Agent Skills: sparse-autoencoder-training

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: PoorRican/dotfiles/sparse-autoencoder-training

Install this agent skill to your local

npx skills add PoorRican/dotfiles --skill sparse-autoencoder-training

Skill Files

The files that make up sparse-autoencoder-training.

Download Skill

More agent skills