64 tagged Mechanistic Interpretability, measured the same way as everything else here.
Browse within: ai-scientist 54ai-systems 54artificial-intelligence 54large-language-models 54ai-research 6
Skill Claude CodeCodex
Workflow 1: Claim-stage pipeline, controlled by two orthogonal axes. BEHAVIORSOURCE selects the behavior stage: given (default; behavior taken from task.md and assumed to hold — no ideation, no novelty, no M0), given-validation (behavior taken from task.md but the experiment plan opens with an M0 phenomenon-validation…
Skill Claude CodeCodex
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENTPLAN.md, routes mechanism family inline (Phase 1.5), implements experiment code, deploys to GPU, and collects initial results. Use when user says "implement experiments", "experiment", "deploy the plan", or has an experiment plan ready to…
Skill Claude CodeCodex
Automated pipeline for generating and refining multiple research hypotheses.
Skill Claude CodeCodex
Scaffold a new steeropathy experiment — agents that communicate through model internals (activations and J-space) instead of text. Use when the user wants to build, add, design, or wire up a new experiment/game/probe in this repo (e.g. "let's have fun with agents who never see each other's output", "add an experiment…
Skill Claude CodeCodex
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.