Sparse Autoencoder Training
If you're diving into mechanistic interpretability or trying to understand what's actually going on inside neural networks, this gets you up and running with SAELens, Anthropic's library for training sparse autoencoders. The core idea is decomposing polysemantic neurons (ones that fire for multiple unrelated concepts) into sparse, interpretable features. It's based on research showing you can extract monosemantic features from superposition, making model internals way more readable. The skill wraps the SAELens library (1,100+ GitHub stars), so you're working with battle-tested code. Honestly most useful if you're doing AI safety research or need to peek under the hood of transformers, less so for standard ML workflows.
- skills.sh installs
- 298
- GitHub stars
- 33.2K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add davila7/claude-code-templates --skill sparse-autoencoder-training --agent claude-codeInstalls into .claude/skills of the current project.
Files
If you're diving into mechanistic interpretability or trying to understand what's actually going on inside neural networks, this gets you up and running with SAELens, Anthropic's library for training sparse autoencoders. The core idea is decomposing polysemantic neurons (ones that fire for multiple unrelated concepts) into sparse, interpretable features. It's based on research showing you can extract monosemantic features from superposition, making model internals way more readable. The skill wraps the SAELens library (1,100+ GitHub stars), so you're working with battle-tested code. Honestly most useful if you're doing AI safety research or need to peek under the hood of transformers, less so for standard ML workflows.
Browse the repository on GitHubSponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/davila7/claude-code-templates
- First seen
- Jun 3, 2026
More from davila7/claude-code-templates
All 618- Mamba Architecture297
- Rdkit297
- Scikit Bio297
- Agent Management296
- Kegg Database295
- Torch Geometric294
- Langfuse291
- Commit Work290
- Quality Manager Qmr290
- Tdd Workflow290
- Get Available Resources289
- Gwas Database289
- Pubchem Database288
- Railway Status288
- Signup Flow Cro288
- Pyvene Interventions287
- Paywall Upgrade Cro286
- Viral Generator Builder285
- Loki Mode284
- Meeting Insights Analyzer284
- Railway Docs284
- Railway New284
- Onboarding Cro283
- Bioservices282
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs