saelens Skill
Train sparse autoencoders to interpret model features. Published by NousResearch in hermes-agent.
Decision snapshot
Is this a fit?
Research, Includes SKILL.md, Reusable instructions
Compatibility not yet detected.
Permission behavior not yet detected.
Copy skill directory
29 days ago · MIT license
No specific cautions were detected. Review the source and requested permissions before installing.
What is saelens Skill?
Train sparse autoencoders to interpret model features. 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. See how SkillIndex evaluates profiles.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Research
- Research use cases
Declared skill metadata
- Declared author: Orchestra Research
- Declared license: MIT
- Source file: optional-skills/mlops/saelens/SKILL.md
These fields retain source and confidence evidence from the indexed SKILL.md.
Compatibility and setup
- Install or run with Copy skill directory
When to use saelens 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
Train sparse autoencoders to interpret model features.
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
Verified compatibility and discovery
Frequently asked questions
What is saelens?
saelens is a open-source AI agent skill with Copy skill directory. Train sparse autoencoders to interpret model features.
Who is saelens best for?
saelens is best for reusing agent instructions, scripts, and references, research workflows.
How do I install saelens?
Install or run saelens using Copy skill directory. Check saelens for the latest setup command.
Is saelens actively maintained?
saelens may need a closer maintenance check before production use.
Project health auto-fetched from the source repository.
Maintain this resource?
Review this source-backed profile, send a correction with evidence, or link to it from your documentation. Claims verify your relationship to the project; profile facts still require source evidence and editorial review.
