Agent Skills: mechanistic-interpretability-transformer-lens

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.

ID: davila7/claude-code-templates/mechanistic-interpretability-transformer-lens

Install this agent skill to your local

npx skills add davila7/claude-code-templates --skill mechanistic-interpretability-transformer-lens

Skill Files

The files that make up mechanistic-interpretability-transformer-lens.

Download Skill

More agent skills