method
active
method:mean-activation-patching-interventionMean-activation patching intervention
Substitutes mean activation for count c to modify perceived counts.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Substitute activations to observe effects.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Standard method in mechanistic interpretability that intervenes on activations; VPD flips this paradigm by patching parameters.
- The general experimental approach of intervening along geometrically-defined paths rather than single-point or linear-direction interventions
- Intervening in model forward pass by adding/subtracting probe direction to group (b) hidden states to flip truth judgments
- Method of shifting hidden state activations along probe directions to cause the model to treat false statements as true and vice versa; evaluated on OOD inputs
- Methods that intentionally introduce divergent representations to test sufficiency and completeness of circuits
- Internal representations of the model on which probes operate; the method uses activations to rank datapoints.
- Fundamental operation for causal abstraction analysis; forces neurons to take values from source inputs to create counterfactuals.
- Property that additive modifications to activations affect all downstream computations, enabling tractable behavioral control