← Todos los skills

mechanistic-interpretability-nnsight

ComunidadMIT

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.

El ZIP contiene solo este skill. Está en GitHub Releases del repo público orlandoneto/agent-skills — Ontoom es la vitrina. El crawler diario actualiza el catálogo.

Cómo instalar

  1. Descarga el ZIP y extrae la carpeta del skill.
  2. Cursor: .agents/skills/aitmpl-mechanistic-interpretability-nnsight/ o .cursor/skills/aitmpl-mechanistic-interpretability-nnsight/
  3. Claude Code: .claude/skills/aitmpl-mechanistic-interpretability-nnsight/
  4. Otras IAs: .agents/skills/aitmpl-mechanistic-interpretability-nnsight/
cursorclaude-codecodexgeminiany

Otros skills de esta colección

Otras colecciones

  • mechanistic-interpretability-pyvene

    Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

  • mechanistic-interpretability-saelens

    Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

  • mechanistic-interpretability-transformer-lens

    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.

  • meeting-notes-structure

    Produces meeting notes that capture decisions and action items — not transcription. Attendees, agenda, decisions, action items with owners and deadlines. Use when a user needs notes from a meeting that's about to happen, is happening, or just ended, or wants a template for recurring meetings.

  • memory-search

    Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search memory", "what did we discuss", "remember when", "find previous conversation", "check history", or before starting work to recall prior decisions.

  • ml-paper-writing

    Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.