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.

Links

• Roles: quantum-ml-engineer
• Source repo: Orchestra-Research/AI-Research-SKILLs
• Same repo: axolotl, deepspeed, distributed-llm-pretraining-torchtitan, fine-tuning-openvla-oft, fine-tuning-serving-openpi, awq-quantization, gguf-quantization, gptq
• Registry seed skills for this role: quantum-ml-engineer seed skills