Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features.
sparse-autoencoder-trainingProvides 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.Category: ml-evaluation-and-safety · License: MIT · Version: 1.0.0
npx research-agent-skills install sparse-autoencoder-training
npx skills add KalarisLabs/research-agent-skills --skill sparse-autoencoder-training