Back to tags
Tag

Agent Skills with tag: Interpretability

5 skills match this tag. Use tags to discover related Agent Skills and explore similar workflows.

mechanistic-interpretability-nnsight

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.

[nnsightNDIFRemoteExecution
Orchestra Research
Orchestra Research
33,1943,891

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.

[SparseAutoencodersSAEMechanistic
Orchestra Research
Orchestra Research
33,1943,891

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.

[MechanisticInterpretabilityTransformerLensActivation
Orchestra Research
Orchestra Research
33,1943,891

sparse-autoencoder-training

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.

[SparseAutoencodersSAEMechanistic
poorrican
poorrican
0

sparse-autoencoder-training

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.

[SparseAutoencodersSAEMechanistic
PoorRican
PoorRican
0