sparse-autoencoder-training
sparse-autoencoder-training is a Model training & evaluation skill for AI agents, published by math-inc in the OpenGauss repository on GitHub. Skillspace rates sparse-autoencoder-training B (81/100) and it passed the safety scan; the rating is based on static analysis only.
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.
- Grade
- B
- Quality
- 81 / 100
- Safety
- Passed
- GitHub stars
- 1,237
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 96 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.