sparse-autoencoder-training Skill
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. Published by NousResearch in hermes-agent.
What is sparse-autoencoder-training Skill?
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. Published by NousResearch in hermes-agent. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Research
- Research use cases
Technical details
- Install or run with Copy skill directory
When to use sparse-autoencoder-training Skill
- Use it for research.
Built with
Editorial notes
Source
- Creator: NousResearch
- Repository: NousResearch/hermes-agent
- Skill file: optional-skills/mlops/saelens/SKILL.md
What it does
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.
Skill instructions
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. SAEs solve this by decomposing dense activations into sparse, monosemantic features - typically only a small number of features activate for any given input, and each feature corresponds to an interpretable concept. When to Use SAELens Use SAELens when you need to: - Discover interpretable features in model activations - Understand what concepts
Explore related resources
Frequently asked questions
What is sparse-autoencoder-training?
sparse-autoencoder-training is a open-source AI agent skill with Copy skill directory. Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features.
Who is sparse-autoencoder-training best for?
sparse-autoencoder-training is best for reusing agent instructions, scripts, and references, research workflows.
How do I install sparse-autoencoder-training?
Install or run sparse-autoencoder-training using Copy skill directory. Check sparse-autoencoder-training for the latest setup command.
Is sparse-autoencoder-training actively maintained?
sparse-autoencoder-training may need a closer maintenance check before production use.
Auto-fetched from GitHub.
