@orchestra-research/transformer-lens-interpretability

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

View in AI SkillSafe app
Scanned · no findings
0 downloads
0 stars
0 demos
SKILL.md

Embed badges

Add these to your README to show the skill's verification status.

SkillSafe verified badge
Verified badge
[![SkillSafe verified badge](https://api.skillsafe.ai/v1/badge/@orchestra-research/transformer-lens-interpretability/verified)](https://skillsafe.ai/skill/@orchestra-research/transformer-lens-interpretability/)
Installs badge
Installs badge
[![Installs badge](https://api.skillsafe.ai/v1/badge/@orchestra-research/transformer-lens-interpretability/installs)](https://skillsafe.ai/skill/@orchestra-research/transformer-lens-interpretability/)
Scan badge
Scan badge
[![Scan badge](https://api.skillsafe.ai/v1/badge/@orchestra-research/transformer-lens-interpretability/scan)](https://skillsafe.ai/skill/@orchestra-research/transformer-lens-interpretability/)
Eval pass rate badge
Eval pass rate
[![Eval pass rate badge](https://api.skillsafe.ai/v1/badge/@orchestra-research/transformer-lens-interpretability/eval)](https://skillsafe.ai/skill/@orchestra-research/transformer-lens-interpretability/)