nnsight-remote-interpretability
FeaturedProvides 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.
Install
Quality Score: 99/100
Skill Content
Details
- Author
- davila7
- Repository
- davila7/claude-code-templates
- Created
- 1 years ago
- Last Updated
- today
- Language
- Python
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
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.
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.
ml-interpretability
Mechanistic interpretability for neural networks: activation caching, hook points, causal tracing, activation patching, interchange interventions (DAS/IIT), and sparse autoencoders (SAEs). Covers TransformerLens, nnsight (including NDIF remote execution), pyvene, and SAELens. Triggers on 'TransformerLens', 'HookedTransformer', 'nnsight', 'NDIF', 'pyvene', 'SAELens', 'activation patching', 'causal tracing', 'circuit analysis', 'sparse autoencoder', 'feature steering', or 'mechanistic interpretability'.