mechanistic-interpretability-transformer-lens
80 / 100 · Low risk
Fine to try.
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.
Partially scanned — some files couldn't be read; we'll retry on the next scan
What this skill can do
Downloads and installs other software
Runs commands on your computer
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'mechanistic-interpretability-transformer-lens' ] || [ -L ~/.agents/skills/'mechanistic-interpretability-transformer-lens' ]; then echo 'A skill folder named mechanistic-interpretability-transformer-lens already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/aicodedecode/awesome-muse-skills' "$d" && git -C "$d" checkout --quiet 'faf37c0859ebf627bfcb5225e8057d088691e0ae' -- 'skills-imported/mechanistic-interpretability-transformer-lens' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills-imported/mechanistic-interpretability-transformer-lens' ~/.agents/skills/'mechanistic-interpretability-transformer-lens' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'mechanistic-interpretability-transformer-lens' ~/.claude/skills/'mechanistic-interpretability-transformer-lens' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/aicodedecode/awesome-muse-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | faf37c0 | 80 |