Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
sparse-autoencoder-training
sparse-autoencoder-training is an open-source productivity skill for Claude Code and compatible agents, published by Orchestra-Research. Its author describes it as: “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 superpo…”. The project has 12k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add Orchestra-Research/AI-Research-SKILLs`.
What sparse-autoencoder-training does
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.
Installation
Add sparse-autoencoder-training to your agent with:
/plugin marketplace add Orchestra-Research/AI-Research-SKILLsAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
What's inside
The SKILL.md for sparse-autoencoder-training is organised into these sections:
- The Problem: Polysemanticity & Superposition
- When to Use SAELens
- Installation
- Core Concepts
- What SAEs Learn
- Key Validation (Anthropic Research)
- Workflow 1: Loading and Analyzing Pre-trained SAEs
- Step-by-Step
- Available Pre-trained SAEs
- Checklist
- Workflow 2: Training a Custom SAE
- Key Hyperparameters
When to use it
Reach for sparse-autoencoder-training when you want productivity help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Clear MIT license — safe to read and adapt
- Ships in Orchestra-Research/AI-Research-SKILLs, an established project with 11,807 GitHub stars
- Actively maintained (recent commits)
Topics
Frequently asked questions
- What does sparse-autoencoder-training do?
- 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.
- How do I install sparse-autoencoder-training?
- Run /plugin marketplace add Orchestra-Research/AI-Research-SKILLs in your agent, then reload your skills. Review the source at https://github.com/Orchestra-Research/AI-Research-SKILLs before installing.
- Is sparse-autoencoder-training free to use?
- Yes. sparse-autoencoder-training is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Where does sparse-autoencoder-training come from?
- sparse-autoencoder-training ships inside Orchestra-Research/AI-Research-SKILLs, a repository that contains 41 catalogued skills in total. The repository's 11,807 GitHub stars apply to that whole collection, not to this skill on its own.
Related skills
More Productivity →Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.