Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activ…
Part of AI Research Skills (Orchestra)Pack · 98 skills
by Orchestra-Research· AI & agentsUnclaimed · Yours? Claim it
About
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.
Skills people install alongside sparse-autoencoder-training.
Runs on your machine.
Runs on your machine.
Runs on your machine.
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.copilot/skills/sparse-autoencoder-training
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.cursor/skills/sparse-autoencoder-training
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.claude/skills/sparse-autoencoder-training
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs /plugin install rag@ai-research-skills
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.agents/skills/sparse-autoencoder-training
Runs on your machine.
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.gemini/skills/sparse-autoencoder-training
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens .agents/skills/sparse-autoencoder-training
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.openclaw/skills/sparse-autoencoder-training
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.config/opencode/skills/sparse-autoencoder-training
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.hermes/skills/sparse-autoencoder-training
Scanned and passed · checked 48 min ago
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
Scanned on every change, and again when our rules improve.
No reviews yet. Used sparse-autoencoder-training? Say how it went.
Write a reviewSkills people install alongside sparse-autoencoder-training.
Has your agent write a tight, ready-to-paste prompt for the AI tool you name, from Claude Code and Cursor to Midjourney and Sora.
Turns a task into a copy-ready /goal command for Claude Code or Codex, with a checkable finish line and a stop bound.
The .NET team's skill for picking the right AI or ML stack in .NET 8+ apps, from ML.NET to Microsoft.Extensions.AI and Agent Framework.
Turn a repeated workflow, prompt set or SOP into a tested, packaged agent skill, or audit and improve a skill you already have.
Nobody has shared how they use sparse-autoencoder-training yet.
Security scan
Passed
Safe to install in every agent it supports. Runs in your agent, as instructions.