Skill · em Dados, IA e pesquisa

nnsight-remote-interpretability

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.

Procedência

Antes de instalar

4 arquivos · 29,4 KB · só texto, nenhum script

Instalar na sua CLI

O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/skills/nnsight-remote-interpretability/.

d=".claude/skills/nnsight-remote-interpretability"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/mechanistic-interpretability-nnsight"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api.md" "$u/references/api.md" \
  -o "$d/references/README.md" "$u/references/README.md" \
  -o "$d/references/tutorials.md" "$u/references/tutorials.md"

Global: instala em ~/.claude/skills/nnsight-remote-interpretability/.

d="$HOME/.claude/skills/nnsight-remote-interpretability"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/mechanistic-interpretability-nnsight"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api.md" "$u/references/api.md" \
  -o "$d/references/README.md" "$u/references/README.md" \
  -o "$d/references/tutorials.md" "$u/references/tutorials.md"

Codex

Neste projeto: instala em .agents/skills/nnsight-remote-interpretability/.

d=".agents/skills/nnsight-remote-interpretability"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/mechanistic-interpretability-nnsight"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api.md" "$u/references/api.md" \
  -o "$d/references/README.md" "$u/references/README.md" \
  -o "$d/references/tutorials.md" "$u/references/tutorials.md"

Global: instala em ~/.agents/skills/nnsight-remote-interpretability/.

d="$HOME/.agents/skills/nnsight-remote-interpretability"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/mechanistic-interpretability-nnsight"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api.md" "$u/references/api.md" \
  -o "$d/references/README.md" "$u/references/README.md" \
  -o "$d/references/tutorials.md" "$u/references/tutorials.md"

Antigravity

Neste projeto: instala em .agents/skills/nnsight-remote-interpretability/.

d=".agents/skills/nnsight-remote-interpretability"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/mechanistic-interpretability-nnsight"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api.md" "$u/references/api.md" \
  -o "$d/references/README.md" "$u/references/README.md" \
  -o "$d/references/tutorials.md" "$u/references/tutorials.md"

Global: instala em ~/.gemini/antigravity-cli/skills/nnsight-remote-interpretability/.

d="$HOME/.gemini/antigravity-cli/skills/nnsight-remote-interpretability"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/mechanistic-interpretability-nnsight"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/api.md" "$u/references/api.md" \
  -o "$d/references/README.md" "$u/references/README.md" \
  -o "$d/references/tutorials.md" "$u/references/tutorials.md"

Peça ao Rook

Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.nnsight-remote-interpretability

Prévia do SKILL.md

---
name: nnsight-remote-interpretability
description: 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.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [nnsight, NDIF, Remote Execution, Mechanistic Interpretability, Model Internals]
dependencies: [nnsight>=0.5.0, torch>=2.0.0]
---

# nnsight: Transparent Access to Neural Network Internals

nnsight (/ɛn.saɪt/) enables researchers to interpret and manipulate the internals of any PyTorch model, with the unique capability of running the same code locally on small models or remotely on massive models (70B+) via NDIF.

**GitHub**: [ndif-team/nnsight](https://github.com/ndif-team/nnsight) (730+ stars)
**Paper**: [NNsight and NDIF: Democratizing Access to Foundation Model Internals](https://arxiv.org/abs/2407.14561) (ICLR 2025)

## Key Value Proposition

**Write once, run anywhere**: The same interpretability code works on GPT-2 locally or Llama-3.1-405B remotely. Just toggle `remote=True`.

```python
# Local execution (small model)
with model.trace("Hello world"):
    hidden = model.transformer.h[5].output[0].save()

# Remote execution (massive model) - same code!
with model.trace("Hello world", remote=True):
    hidden = model.model.layers[40].output[0].save()
```

## When to Use nnsight

**Use nnsight when you need to:**
- Run interpretability experiments on models too large for local GPUs (70B, 405B)
- Work with any PyTorch architecture (transformers, Mamba, custom models)
- Perform multi-token generation interventions
- Share activations between different prompts
- Access full model internals without reimplementation
…

Ver todo o marketplace