New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

TransformerLens Interpretability

by Orchestra-Research in Orchestra-Research/AI-Research-SKILLs

Guides mechanistic interpretability work with TransformerLens: loading models, caching activations, using HookPoints, activation patching and attention-pattern analysis.

MITAuto-check passedAI & LLM Engineering

Install TransformerLens Interpretability

skills CLI
$ npx skills add Orchestra-Research/AI-Research-SKILLs --skill transformer-lens-interpretability -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Orchestra-Research/AI-Research-SKILLs transformer-lens-interpretability --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/04-mechanistic-interpretability/transformer-lens .claude/skills/transformer-lens-interpretability && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
transformer-lens-interpretability
GitHub stars
13k
Used in
3 other repos
Token cost
~3k tokens
SKILL.md length
535 words
Files
4 (incl. references)
Skills in repo
96
Repo updated
First seen
Licence
MIT

At a glance

Guides mechanistic interpretability work with TransformerLens: loading models, caching activations, using HookPoints, activation patching and attention-pattern analysis.

  • Running activation patching or causal tracing on a small language model
  • SKILL.md covers When to Use TransformerLens, Installation, Core Concepts and Workflow 1: Activation…, plus 8 more sections
  • Calls pip; reaches github.com; needs HF_TOKEN
  • Inspecting attention patterns for a specific prompt

What it does

The skill introduces TransformerLens, a library for mechanistic interpretability on GPT-style language models that exposes a HookPoint on every activation. It lists when to use it: reverse-engineering learned algorithms, activation patching and causal tracing, studying attention patterns and information flow, analyzing circuits such as induction heads and the IOI circuit, caching intermediate activations and direct logit attribution.

Setup is pip install transformer-lens. The main class is HookedTransformer, which wraps a model, and run_with_cache returns logits plus a cache of activations whose keys, such as resid_pre, resid_mid, resid_post and attn_out per layer, are tabulated with their shapes. A table lists supported model families, covering more than 50 models including GPT-2, LLaMA, Pythia, Mistral, Phi, Qwen, OPT and Gemma.

It also points elsewhere when TransformerLens fits poorly: nnsight or pyvene for non-transformer architectures or higher-level causal interventions, SAELens for sparse autoencoders, and nnsight with NDIF for remote runs on very large models. Reference files include api.md and tutorials.md.

When your agent uses it

  • Running activation patching or causal tracing on a small language model
  • Inspecting attention patterns for a specific prompt
  • Caching intermediate activations to look at the residual stream
  • Studying circuits such as induction heads

Example prompts

  • “Load gpt2 in TransformerLens and cache the activations for the prompt 'The Eiffel Tower is in'.”
  • “Run activation patching between a clean and a corrupted prompt and show which layers matter.”
  • “Plot the attention patterns for the induction heads in GPT-2.”

Requirements

  • Python with the transformer-lens package

What it can do on your machine

Read from SKILL.md and the folder at commit 773a529. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    Also links to:

    • transformerlensorg.github.io
    • transformer-circuits.pub
    • colab.research.google.com
    • arena-foundation.github.io
    • arxiv.org
    • neelnanda.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • HF_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

TransformerLens Interpretability loads about 3k tokens when it runs, and up to ~8k if it reads all its reference files. Until then it costs about 81 tokens; SKILL.md has 535 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Orchestra-Research/AI-Research-SKILLs at commit 773a529, republished under its MIT licence (© Orchestra-Research). 535 words, ~3,007 tokens.

Download SKILL.mdSave it as .claude/skills/transformer-lens-interpretability/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
transformer-lens-interpretability
description
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
version
1.0.0
author
Orchestra Research
license
MIT
tags
Mechanistic Interpretability, TransformerLens, Activation Patching, Circuit Analysis
dependencies
transformer-lens>=2.0.0, torch>=2.0.0

TransformerLens: Mechanistic Interpretability for Transformers

TransformerLens is the de facto standard library for mechanistic interpretability research on GPT-style language models. Created by Neel Nanda and maintained by Bryce Meyer, it provides clean interfaces to inspect and manipulate model internals via HookPoints on every activation.

GitHub: TransformerLensOrg/TransformerLens (2,900+ stars)

When to Use TransformerLens

Use TransformerLens when you need to:

  • Reverse-engineer algorithms learned during training
  • Perform activation patching / causal tracing experiments
  • Study attention patterns and information flow
  • Analyze circuits (e.g., induction heads, IOI circuit)
  • Cache and inspect intermediate activations
  • Apply direct logit attribution

Consider alternatives when:

  • You need to work with non-transformer architectures → Use nnsight or pyvene
  • You want to train/analyze Sparse Autoencoders → Use SAELens
  • You need remote execution on massive models → Use nnsight with NDIF
  • You want higher-level causal intervention abstractions → Use pyvene

Installation

bash
pip install transformer-lens

For development version:

bash
pip install git+https://github.com/TransformerLensOrg/TransformerLens

Core Concepts

HookedTransformer

The main class that wraps transformer models with HookPoints on every activation:

python
from transformer_lens import HookedTransformer

# Load a model
model = HookedTransformer.from_pretrained("gpt2-small")

# For gated models (LLaMA, Mistral)
import os
os.environ["HF_TOKEN"] = "your_token"
model = HookedTransformer.from_pretrained("meta-llama/Llama-2-7b-hf")
Supported Models (50+)
FamilyModels
GPT-2gpt2, gpt2-medium, gpt2-large, gpt2-xl
LLaMAllama-7b, llama-13b, llama-2-7b, llama-2-13b
EleutherAIpythia-70m to pythia-12b, gpt-neo, gpt-j-6b
Mistralmistral-7b, mixtral-8x7b
Othersphi, qwen, opt, gemma
Activation Caching

Run the model and cache all intermediate activations:

python
# Get all activations
tokens = model.to_tokens("The Eiffel Tower is in")
logits, cache = model.run_with_cache(tokens)

# Access specific activations
residual = cache["resid_post", 5]  # Layer 5 residual stream
attn_pattern = cache["pattern", 3]  # Layer 3 attention pattern
mlp_out = cache["mlp_out", 7]  # Layer 7 MLP output

# Filter which activations to cache (saves memory)
logits, cache = model.run_with_cache(
    tokens,
    names_filter=lambda name: "resid_post" in name
)
ActivationCache Keys
Key PatternShapeDescription
resid_pre, layer[batch, pos, d_model]Residual before attention
resid_mid, layer[batch, pos, d_model]Residual after attention
resid_post, layer[batch, pos, d_model]Residual after MLP
attn_out, layer[batch, pos, d_model]Attention output
mlp_out, layer[batch, pos, d_model]MLP output
pattern, layer[batch, head, q_pos, k_pos]Attention pattern (post-softmax)
q, layer[batch, pos, head, d_head]Query vectors
k, layer[batch, pos, head, d_head]Key vectors
v, layer[batch, pos, head, d_head]Value vectors

Workflow 1: Activation Patching (Causal Tracing)

Identify which activations causally affect model output by patching clean activations into corrupted runs.

Step-by-Step
python
from transformer_lens import HookedTransformer, patching
import torch

model = HookedTransformer.from_pretrained("gpt2-small")

# 1. Define clean and corrupted prompts
clean_prompt = "The Eiffel Tower is in the city of"
corrupted_prompt = "The Colosseum is in the city of"

clean_tokens = model.to_tokens(clean_prompt)
corrupted_tokens = model.to_tokens(corrupted_prompt)

# 2. Get clean activations
_, clean_cache = model.run_with_cache(clean_tokens)

# 3. Define metric (e.g., logit difference)
paris_token = model.to_single_token(" Paris")
rome_token = model.to_single_token(" Rome")

def metric(logits):
    return logits[0, -1, paris_token] - logits[0, -1, rome_token]

# 4. Patch each position and layer
results = torch.zeros(model.cfg.n_layers, clean_tokens.shape[1])

for layer in range(model.cfg.n_layers):
    for pos in range(clean_tokens.shape[1]):
        def patch_hook(activation, hook):
            activation[0, pos] = clean_cache[hook.name][0, pos]
            return activation

        patched_logits = model.run_with_hooks(
            corrupted_tokens,
            fwd_hooks=[(f"blocks.{layer}.hook_resid_post", patch_hook)]
        )
        results[layer, pos] = metric(patched_logits)

# 5. Visualize results (layer x position heatmap)
Checklist
  • Define clean and corrupted inputs that differ minimally
  • Choose metric that captures behavior difference
  • Cache clean activations
  • Systematically patch each (layer, position) combination
  • Visualize results as heatmap
  • Identify causal hotspots
Show full SKILL.md (216 more words)Show less

Workflow 2: Circuit Analysis (Indirect Object Identification)

Replicate the IOI circuit discovery from "Interpretability in the Wild".

Step-by-Step
python
from transformer_lens import HookedTransformer
import torch

model = HookedTransformer.from_pretrained("gpt2-small")

# IOI task: "When John and Mary went to the store, Mary gave a bottle to"
# Model should predict "John" (indirect object)

prompt = "When John and Mary went to the store, Mary gave a bottle to"
tokens = model.to_tokens(prompt)

# 1. Get baseline logits
logits, cache = model.run_with_cache(tokens)

john_token = model.to_single_token(" John")
mary_token = model.to_single_token(" Mary")

# 2. Compute logit difference (IO - S)
logit_diff = logits[0, -1, john_token] - logits[0, -1, mary_token]
print(f"Logit difference: {logit_diff.item():.3f}")

# 3. Direct logit attribution by head
def get_head_contribution(layer, head):
    # Project head output to logits
    head_out = cache["z", layer][0, :, head, :]  # [pos, d_head]
    W_O = model.W_O[layer, head]  # [d_head, d_model]
    W_U = model.W_U  # [d_model, vocab]

    # Head contribution to logits at final position
    contribution = head_out[-1] @ W_O @ W_U
    return contribution[john_token] - contribution[mary_token]

# 4. Map all heads
head_contributions = torch.zeros(model.cfg.n_layers, model.cfg.n_heads)
for layer in range(model.cfg.n_layers):
    for head in range(model.cfg.n_heads):
        head_contributions[layer, head] = get_head_contribution(layer, head)

# 5. Identify top contributing heads (name movers, backup name movers)
Checklist
  • Set up task with clear IO/S tokens
  • Compute baseline logit difference
  • Decompose by attention head contributions
  • Identify key circuit components (name movers, S-inhibition, induction)
  • Validate with ablation experiments

Workflow 3: Induction Head Detection

Find induction heads that implement [A][B]...[A] → [B] pattern.

python
from transformer_lens import HookedTransformer
import torch

model = HookedTransformer.from_pretrained("gpt2-small")

# Create repeated sequence: [A][B][A] should predict [B]
repeated_tokens = torch.tensor([[1000, 2000, 1000]])  # Arbitrary tokens

_, cache = model.run_with_cache(repeated_tokens)

# Induction heads attend from final [A] back to first [B]
# Check attention from position 2 to position 1
induction_scores = torch.zeros(model.cfg.n_layers, model.cfg.n_heads)

for layer in range(model.cfg.n_layers):
    pattern = cache["pattern", layer][0]  # [head, q_pos, k_pos]
    # Attention from pos 2 to pos 1
    induction_scores[layer] = pattern[:, 2, 1]

# Heads with high scores are induction heads
top_heads = torch.topk(induction_scores.flatten(), k=5)

Common Issues & Solutions

Issue: Hooks persist after debugging
python
# WRONG: Old hooks remain active
model.run_with_hooks(tokens, fwd_hooks=[...])  # Debug, add new hooks
model.run_with_hooks(tokens, fwd_hooks=[...])  # Old hooks still there!

# RIGHT: Always reset hooks
model.reset_hooks()
model.run_with_hooks(tokens, fwd_hooks=[...])
Issue: Tokenization gotchas
python
# WRONG: Assuming consistent tokenization
model.to_tokens("Tim")  # Single token
model.to_tokens("Neel")  # Becomes "Ne" + "el" (two tokens!)

# RIGHT: Check tokenization explicitly
tokens = model.to_tokens("Neel", prepend_bos=False)
print(model.to_str_tokens(tokens))  # ['Ne', 'el']
Issue: LayerNorm ignored in analysis
python
# WRONG: Ignoring LayerNorm
pre_activation = residual @ model.W_in[layer]

# RIGHT: Include LayerNorm
ln_scale = model.blocks[layer].ln2.w
ln_out = model.blocks[layer].ln2(residual)
pre_activation = ln_out @ model.W_in[layer]
Issue: Memory explosion with large models
python
# Use selective caching
logits, cache = model.run_with_cache(
    tokens,
    names_filter=lambda n: "resid_post" in n or "pattern" in n,
    device="cpu"  # Cache on CPU
)

Key Classes Reference

ClassPurpose
HookedTransformerMain model wrapper with hooks
ActivationCacheDictionary-like cache of activations
HookedTransformerConfigModel configuration
FactoredMatrixEfficient factored matrix operations

Integration with SAELens

TransformerLens integrates with SAELens for Sparse Autoencoder analysis:

python
from transformer_lens import HookedTransformer
from sae_lens import SAE

model = HookedTransformer.from_pretrained("gpt2-small")
sae = SAE.from_pretrained("gpt2-small-res-jb", "blocks.8.hook_resid_pre")

# Run with SAE
tokens = model.to_tokens("Hello world")
_, cache = model.run_with_cache(tokens)
sae_acts = sae.encode(cache["resid_pre", 8])

Reference Documentation

For detailed API documentation, tutorials, and advanced usage, see the references/ folder:

FileContents
references/README.mdOverview and quick start guide
references/api.mdComplete API reference for HookedTransformer, ActivationCache, HookPoints
references/tutorials.mdStep-by-step tutorials for activation patching, circuit analysis, logit lens

External Resources

Tutorials
Papers
Official Documentation

Version Notes

  • v2.0: Removed HookedSAE (moved to SAELens)
  • v3.0 (alpha): TransformerBridge for loading any nn.Module

© Orchestra-Research, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in 04-mechanistic-interpretability/transformer-lens of Orchestra-Research/AI-Research-SKILLs.

  • SKILL.md
  • references/README.md
  • references/api.md
  • references/tutorials.md

Open the folder on GitHubat commit 773a529

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in Orchestra-Research/AI-Research-SKILLs, which our catalogue first saw on October 7, 2026.

Compare with similar skills

TransformerLens Interpretability next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

TransformerLens Interpretability compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
TransformerLens Interpretability this skillOrchestra-Research/AI-Research-SKILLs13k3 repos~3kAutomated safety check: PassMIT
Alphagenome Predictionsgenomicsxai/alphagenome-pytorch162—~868Automated safety check: PassApache-2.0
Bio Atac Seq Deep Learning AtacGPTomics/bioSkills1.2k2 repos~5kAutomated safety check: PassMIT
Bio Clip Seq Clip Deep LearningGPTomics/bioSkills1.2k2 repos~4.7kAutomated safety check: PassMIT
Bio Chipseq Chip Deep LearningGPTomics/bioSkills1.2k2 repos~3.8kAutomated safety check: PassMIT
Paddle Design DistributedPaddlePaddle/Paddle24k—~660Automated safety check: PassApache-2.0

Similar skills

  • Alphagenome Predictions

    genomicsxai/alphagenome-pytorch

    Run AlphaGenome-PyTorch to get genomic track predictions — via the agt predict CLI (single locus, BED regions, whole chromosomes, raw FASTA sequences, or per-gene count tables/AnnData), variant…

    162 GitHub stars~868 tokensUpdated 25 days ago
    AI & LLM EngineeringAuto-check passed

  • Bio Atac Seq Deep Learning Atac

    GPTomics/bioSkills

    Sequence-based deep learning for ATAC-seq using chromBPNet, BPNet, scBasset, or Enformer.

    1.2k GitHub starsUsed in 2 repos~5k tokens
    AI & LLM EngineeringAuto-check passed

  • Bio Clip Seq Clip Deep Learning

    GPTomics/bioSkills

    Predict RBP binding from RNA sequence using deep learning models (RBPNet sequence-to-signal, RNAProt RNN, GraphProt2 GCN with structure, DeepCLIP, DeepRiPe multi-modal CNN) for variant-effect…

    1.2k GitHub starsUsed in 2 repos~4.7k tokens
    AI & LLM EngineeringAuto-check passed

  • Bio Chipseq Chip Deep Learning

    GPTomics/bioSkills

    Trains and applies base-resolution deep learning models on ChIP-seq / ChIP-nexus / CUT&RUN data.

    1.2k GitHub starsUsed in 2 repos~3.8k tokens
    AI & LLM EngineeringAuto-check passed

  • Paddle Design Distributed

    PaddlePaddle/Paddle

    A skill your agent uses when working with Paddle's distributed training system: understanding parallelism strategies (DP, ZeRO, TP, PP, SP), semi-automatic parallel with ProcessMesh + shardtensor…

    24k GitHub stars~660 tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Onnxtxt

    onnx/onnx

    Read or write ONNX text format ("onnxtxt"). An agent skill from onnx/onnx.

    22k GitHub stars~1.3k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from Orchestra-Research/AI-Research-SKILLs

All 96 skills in this repo

  • AudioCraft Audio Generation

    Orchestra-Research/AI-Research-SKILLs

    Generates music from text descriptions with MusicGen and sound effects with AudioGen, using Meta's AudioCraft PyTorch library with melody and style conditioning.

    13k GitHub starsUsed in 8 repos~3.9k tokens
    Auto-check passed

  • LLM Benchmarking with lm-evaluation-harness

    Orchestra-Research/AI-Research-SKILLs

    Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

    13k GitHub starsUsed in 8 repos~3k tokens
    Auto-check passed

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 8 repos~3.3k tokens
    Auto-check passed

  • Chroma Vector Database

    Orchestra-Research/AI-Research-SKILLs

    Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

    13k GitHub starsUsed in 7 repos~2.3k tokens
    Auto-check passed

  • CLIP Image-Text Matching

    Orchestra-Research/AI-Research-SKILLs

    Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

    13k GitHub starsUsed in 7 repos~1.7k tokens
    Auto-check passed

  • Whisper Speech Recognition

    Orchestra-Research/AI-Research-SKILLs

    Transcribes audio with OpenAI's Whisper: 99 languages, translation to English, language detection, six model sizes and word-level timestamps, from Python or the CLI.

    13k GitHub starsUsed in 7 repos~1.9k tokens
    Auto-check: notes

Works with

Categories

Questions about TransformerLens Interpretability

What does TransformerLens Interpretability do?

Guides mechanistic interpretability work with TransformerLens: loading models, caching activations, using HookPoints, activation patching and attention-pattern analysis. The skill introduces TransformerLens, a library for mechanistic interpretability on GPT-style language models that exposes a HookPoint on every activation. It lists when to use it: reverse-engineering learned algorithms, activation patching and causal tracing, studying attention patterns and information flow, analyzing circuits such as induction heads and the IOI circuit, caching intermediate activations and direct logit attribution.

When should I use TransformerLens Interpretability?

TransformerLens Interpretability fits situations like: running activation patching or causal tracing on a small language model; inspecting attention patterns for a specific prompt; caching intermediate activations to look at the residual stream; studying circuits such as induction heads.

How do I install TransformerLens Interpretability in Claude Code?

Run `npx skills add Orchestra-Research/AI-Research-SKILLs --skill transformer-lens-interpretability -a claude-code`. Or copy the skill folder (04-mechanistic-interpretability/transformer-lens in Orchestra-Research/AI-Research-SKILLs) into .claude/skills/transformer-lens-interpretability in your project. Claude Code loads it when a task matches its description.

How do I install TransformerLens Interpretability in Codex?

Run `npx skills add Orchestra-Research/AI-Research-SKILLs --skill transformer-lens-interpretability -a codex`. Or copy the skill folder (04-mechanistic-interpretability/transformer-lens in Orchestra-Research/AI-Research-SKILLs) into .agents/skills/transformer-lens-interpretability in your project. Codex loads it when a task matches its description.

Can I use TransformerLens Interpretability in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Orchestra-Research/AI-Research-SKILLs --skill transformer-lens-interpretability -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/transformer-lens-interpretability, .gemini/skills/transformer-lens-interpretability, .github/skills/transformer-lens-interpretability and .opencode/skills/transformer-lens-interpretability in your project.

What does TransformerLens Interpretability need to run?

Going by SKILL.md and its folder, TransformerLens Interpretability needs the command-line tools its instructions call (pip) and credentials named HF_TOKEN. Our summary lists: Python with the transformer-lens package.

Does TransformerLens Interpretability access the network?

SKILL.md names 7 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: transformerlensorg.github.io, transformer-circuits.pub, colab.research.google.com, arena-foundation.github.io, arxiv.org and neelnanda.io. This is read from the text; nothing was executed.

Is TransformerLens Interpretability safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does TransformerLens Interpretability use?

TransformerLens Interpretability is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does TransformerLens Interpretability use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5k tokens, read only when the agent opens those files.

What are the alternatives to TransformerLens Interpretability?

Skills that share tags, products or a category with TransformerLens Interpretability: Alphagenome Predictions (genomicsxai/alphagenome-pytorch, 162 stars), Bio Atac Seq Deep Learning Atac (GPTomics/bioSkills, 1.2k stars), Bio Clip Seq Clip Deep Learning (GPTomics/bioSkills, 1.2k stars) and Bio Chipseq Chip Deep Learning (GPTomics/bioSkills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains TransformerLens Interpretability?

Orchestra-Research (a GitHub organization) maintains it in Orchestra-Research/AI-Research-SKILLs, which has 13,405 GitHub stars. The repository holds 96 skills in this directory. The repository was last updated on June 16, 2026.

Source: Orchestra-Research/AI-Research-SKILLs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.