mechinterp-summarizer
Convert experiment results to Markdown research notes and optionally update research state with evidence
Browse published AI skills maintained by cesaregarza. Compare skill descriptions and follow each source repository for setup instructions.
Indexed skills
15Repository stars across indexed skills
15Repository forks
0Average repository stars per indexed skill
1Repository stars may repeat across skills from the same repository.
Convert experiment results to Markdown research notes and optionally update research state with evidence
Analyze SAE decoder weights - output influence, feature importance, and decoder similarity
Run credibility checks on feature interpretations including split-half stability and shuffle null tests
Reference skill for Splatoon ability families, AP rungs, token constraints, and domain rules for mechinterp experiments
Manage research state for SAE feature analysis including hypotheses, evidence tracking, and research history
Propose next mechanistic interpretability experiments based on research state, hypotheses, and existing evidence
Domain expert for Splatoon 3 competitive gear abilities and weapon meta. Use when: (1) Labeling or classifying gear build features from SAE analysis, (2) Understanding why specific ability combinations appear i...
Orchestrate a systematic research program to investigate and meaningfully label SAE features
Manage feature labeling workflow - queue management, label storage, similar features, progress tracking
Quick "first look" overview of SAE features - top tokens, activation stats, weapons, families, sample contexts
Reference catalog of recurring SAE feature patterns - check when labeling new features, add new patterns as discovered
Analyze relationships across multiple SAE features - co-activation patterns, shared drivers, and subsystem identification
Execute mechanistic interpretability experiments from JSON specs - family sweeps, itemsets, interactions, minimal cores, validation
Match SAE features between Ultra (24K) and Full (2K) models based on activation patterns and token overlap
Reference for ability family semantic groupings and gameplay meanings
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.