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.
Install
npx skills add davila7/claude-code-templates --skill transformer-lens-interpretabilitynpx skills add davila7/claude-code-templates --skill transformer-lens-interpretability -a claude-code -gnpx skills add davila7/claude-code-templates --skill transformer-lens-interpretability -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/mechanistic-interpretability-transformer-lensgh skill install davila7/claude-code-templates transformer-lens-interpretabilitygit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/mechanistic-interpretability-transformer-lens ~/.claude/skills/transformer-lens-interpretability # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/mechanistic-interpretability-transformer-lens ~/.agents/skills/transformer-lens-interpretability # Codex, Cursor, Gemini CLI, Copilot, OpenCode