attribution-patching

7

ndif-team

Gradient-based approximation to activation patching for scalable circuit analysis. Use when activation patching is too slow or when analyzing many components simultaneously.

logit-lens

7

ndif-team

Decode intermediate layer predictions using the Logit Lens technique. Use when analyzing what a model predicts at each layer, understanding information flow, or visualizing layer-wise processing.

activation-patching

7

ndif-team

Causal intervention via activation patching to identify important model components. Use when determining which layers, heads, or positions are causally responsible for model behavior.

causal-tracing

7

ndif-team

Causal mediation analysis to identify which model components mediate specific behaviors. Use when investigating how information flows through the network and which neurons or layers are causally responsible for outputs.

nnsight-basics

7

ndif-team

Core nnsight concepts for neural network interpretability. Use when setting up models, tracing activations, saving values, or making basic interventions on model internals.

model-steering

7

ndif-team

Control model behavior through persistent edits and steering interventions. Use when modifying model outputs, applying steering vectors, or creating persistently modified model versions.