Agent Skills: mechanistic-interpretability-saelens

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

ID: davila7/claude-code-templates/mechanistic-interpretability-saelens

Install this agent skill to your local

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

Skill Files

The files that make up mechanistic-interpretability-saelens.

Download Skill

More agent skills