# sparse-autoencoder-training

> Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activ…

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.

- Type: Skill
- Made by: Orchestra-Research
- Category: AI & agents
- Formats: Skills
- Version: f70208a
- Source: https://github.com/orchestra-research/ai-research-skills/tree/HEAD/04-mechanistic-interpretability/saelens
- Page: https://pluginboard.ai/skills/sparse-autoencoder-training

## Works with

- ChatGPT
- Claude
- Gemini
- GitHub Copilot
- Cursor
- Claude Code
- Codex
- Antigravity
- Gemini CLI
- Replit
- OpenClaw
- OpenCode
- Hermes Agent

## Install

### ChatGPT

In ChatGPT: Download the sparse-autoencoder-training folder and zip it, then Plugins → Skills → Create → Upload from your computer. Business and Enterprise plans.

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### Claude

In Claude (web or desktop): Download the sparse-autoencoder-training folder and zip the folder itself, then upload it in Customize → Skills.

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### Gemini

In Gemini: Download the sparse-autoencoder-training folder, then at gemini.google.com click Customize → Skills → Create → Upload and pick the folder (or a .zip of it).

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### GitHub Copilot

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.copilot/skills/sparse-autoencoder-training
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### Cursor

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.cursor/skills/sparse-autoencoder-training
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### Claude Code

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.claude/skills/sparse-autoencoder-training
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

Or all of AI Research Skills (Orchestra), in Claude Code:

```text
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs
/plugin install rag@ai-research-skills
```

### Codex

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.agents/skills/sparse-autoencoder-training
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### Antigravity

In Antigravity: Copy the sparse-autoencoder-training folder into ~/.gemini/config/skills (Antigravity app and IDE) or ~/.gemini/antigravity-cli/skills (Antigravity CLI).

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### Gemini CLI

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.gemini/skills/sparse-autoencoder-training
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### Replit

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens .agents/skills/sparse-autoencoder-training
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### OpenClaw

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.openclaw/skills/sparse-autoencoder-training
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### OpenCode

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.config/opencode/skills/sparse-autoencoder-training
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

### Hermes Agent

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/04-mechanistic-interpretability/saelens ~/.hermes/skills/sparse-autoencoder-training
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/04-mechanistic-interpretability/saelens

---
From Pluginboard (https://pluginboard.ai).