Sparse Autoencoder Training

Sparse Autoencoder Training is an AI Engineering skill for Claude Code, published by Orchestra-Research in AI-Research-SKILLs.

11.6K stars838 forkson Orchestra-Research/AI-Research-SKILLsAdded 2026/07/19+1% in starsRepository updated 2026/06/16

View source on GitHub Download repo ZIP

aiai-researchclaudeclaude-codeclaude-skillscodexgeminigpt-5grpohuggingfacemachine-leanringmegatronskillsvllm

Install in seconds

Install Sparse Autoencoder Training

Copy Sparse Autoencoder Training into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/main/04-mechanistic-interpretability/saelens ~/.claude/skills/saelens

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Orchestra-Research/AI-Research-SKILLs.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: 04-mechanistic-interpretability/saelens/SKILL.md in Orchestra-Research/AI-Research-SKILLs
Installs to: ~/.claude/skills/saelens
Collection: One of 50 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Sparse Autoencoder Training does

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

Sparse Autoencoder Training is cataloged under AI Engineering on DirSkills. Sparse Autoencoder Training comes from a repository tagged ai, ai-research, claude, claude-code and claude-skills.

Documentation

README

Excerpt

SAELens: Sparse Autoencoders for Mechanistic Interpretability

SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.

GitHub: jbloomAus/SAELens (1,100+ stars)

The Problem: Polysemanticity & Superposition

Individual neurons in neural networks are polysemantic - they activate in multiple, semantically distinct contexts. This happens because models use superposition to represent more features than they have neurons, making interpretability difficult.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Sparse Autoencoder Training

What else does Orchestra-Research publish alongside Sparse Autoencoder Training?
Sparse Autoencoder Training is one of 50 skills that DirSkills catalogs from Orchestra-Research/AI-Research-SKILLs, the repository it ships in. Its siblings there include AWQ Quantization, Autoresearch and Axolotl. Each one is a separate skill with its own page in this directory, installs the same way Sparse Autoencoder Training does, and is maintained by Orchestra-Research in that same repository. The rest of the collection is listed on the Orchestra-Research/AI-Research-SKILLs page.
How does Sparse Autoencoder Training compare to other AI Engineering skills?
Sparse Autoencoder Training ranks #365 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Sparse Autoencoder Training against them. Open each page to compare what they document and how they install.