Nnsight Remote Interpretability
Skill Verifiziert AktivProvides 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.
To enable researchers and developers to deeply inspect and modify the internal workings of PyTorch neural networks, particularly for large-scale models where local resources are a constraint, through a unified and powerful interpretability framework.
Funktionen
- Interpret and manipulate neural network internals
- Unified API for any PyTorch architecture
- Remote execution on massive models (70B+) via NDIF
- Deferred execution and activation saving
- Gradient-based analysis
Anwendungsfälle
- Running interpretability experiments on models too large for local GPUs
- Analyzing and intervening in any PyTorch model's internal states
- Performing multi-token generation interventions and activation patching
- Sharing activations between different prompts within a single trace
Nicht-Ziele
- Providing a consistent API across all model types (TransformerLens is preferred for this)
- Declarative, shareable interventions (pyvene is preferred for this)
- Training research components like SAEs (SAELens is preferred for this)
- Replacing local experimentation entirely when small models suffice
Trust
- info:Issues AttentionIn the last 90 days, 17 issues were opened and 4 were closed, indicating that maintainers are addressing issues but response time could be improved.
Installation
npx skills add davila7/claude-code-templatesFührt das Vercel skills CLI (skills.sh) via npx aus — benötigt Node.js lokal und mindestens einen installierten skills-kompatiblen Agent (Claude Code, Cursor, Codex, …). Setzt voraus, dass das Repo dem agentskills.io-Format folgt.
Qualitätspunktzahl
VerifiziertVertrauenssignale
Ähnliche Erweiterungen
PyTorch Lightning
100Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
Nnsight Remote Interpretability
99Provides 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.
Pytorch Lightning
99High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
Huggingface Accelerate
99Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
Torch Geometric
98Guide for building Graph Neural Networks with PyTorch Geometric (PyG). Use this skill whenever the user asks about graph neural networks, GNNs, node classification, link prediction, graph classification, message passing networks, heterogeneous graphs, neighbor sampling, or any task involving torch_geometric / PyG. Also trigger when you see imports from torch_geometric, or the user mentions graph convolutions (GCN, GAT, GraphSAGE, GIN), graph data structures, or working with relational/network data. Even if the user just says 'graph learning' or 'geometric deep learning', use this skill.
HuggingFace Accelerate
97Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.