Loading…
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.
sparse-autoencoder-training is an agent skill entry in ChatHome Skills, sourced from GitHub Skill Search and scored 58/100. # SAELens: Sparse Autoencoders for Mechanistic Interpretability SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a techniq. As an agent skill, it packages a reusable instruction set that AI coding agents such as Codex and Claude Code can load to perform this task without hand-written glue code. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding sparse-autoencoder-training to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
codex skill install helix4u/hermes-agent-privateReview the upstream source before running this command.
Scan coverage: Install metadata and the indexed document body.
Automated signals from install metadata and a bounded skill body — not a full code security audit and not a recursive source or dependency review.
# SAELens: Sparse Autoencoders for Mechanistic Interpretability SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing p