Overview
transformer-lens-interpretability is an open-source frontend skill for Claude Code and compatible agents, published by Orchestra-Research. Its author describes it as: “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, s…”. The project has 12k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add Orchestra-Research/AI-Research-SKILLs`.
What transformer-lens-interpretability does
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.
What’s inside
The SKILL.md for transformer-lens-interpretability is organised into these sections:
- When to Use TransformerLens
- Installation
- Core Concepts
- HookedTransformer
- Supported Models (50+)
- Activation Caching
- ActivationCache Keys
- Workflow 1: Activation Patching (Causal Tracing)
- Step-by-Step
- Checklist
- Workflow 2: Circuit Analysis (Indirect Object Identification)
- Workflow 3: Induction Head Detection
Installation
Add transformer-lens-interpretability to your agent with:
/plugin marketplace add Orchestra-Research/AI-Research-SKILLsReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — ships a claude code plugin marketplace
- Codex — declared in the repository topics
License
transformer-lens-interpretability is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in Orchestra-Research/AI-Research-SKILLs, an established project with 11,807 GitHub stars
- Works with Claude Code, Codex
Author
Topics
Frequently asked questions
- What does transformer-lens-interpretability do?
- 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.
- How do I install transformer-lens-interpretability?
- Run /plugin marketplace add Orchestra-Research/AI-Research-SKILLs in your agent, then reload your skills. Review the source at https://github.com/Orchestra-Research/AI-Research-SKILLs before installing.
- Is transformer-lens-interpretability free to use?
- Yes. transformer-lens-interpretability is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does transformer-lens-interpretability work with?
- transformer-lens-interpretability lists Claude Code and Codex — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does transformer-lens-interpretability come from?
- transformer-lens-interpretability ships inside Orchestra-Research/AI-Research-SKILLs, a repository that contains 41 catalogued skills in total. The repository's 11,807 GitHub stars apply to that whole collection, not to this skill on its own.
