Agent Skills: sparse-autoencoder-training
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.
ID: PoorRican/dotfiles/sparse-autoencoder-training
Install this agent skill to your local
Skill Files
The files that make up sparse-autoencoder-training.
More agent skills
- commitCreate well-formatted commits with conventional commit messages and emoji
- n8n:create-prCreates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.
- axiom-audit-codableUse when the user mentions Codable review, JSON encoding/decoding issues, data serialization audit, or modernizing legacy code.
- agileAgile product management, Scrum practices, and team collaboration for iterative product development.
- setup-codemap-cliGuide for setup Codemap CLI for intelligent codebase visualization and navigation
- molfeatMolecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.