Parallel Intervention

Intervention mode where multiple interventions are applied simultaneously to the same base computation graph

Neighborhood — ranked by edge-count

paper

concept

Neural Network Intervention
extends
The fundamental operation of making in-place changes to model activations, placing the model in a counterfactual state

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Serial Interventionconcept0.801
Intervention mode where interventions are applied sequentially, each building on the previous one
linear interventionconcept0.784
Manipulation of activations along a straight line; shown to fail when it crosses voids, in contrast to manifold-following interventions.
Interchange Interventionmethod0.781
Fundamental operation for causal abstraction analysis; forces neurons to take values from source inputs to create counterfactuals.
Subspace Interventionconcept0.775
Intervention targeting specific dimensional subsets of activation vectors rather than full representations
Serializable Interventionconcept0.771
pyvene's approach of storing interventions as shareable serialized objects rather than runtime code
Distributed Interchange Interventionmethod0.768
Extends interchange interventions to non-standard bases by rotating representations, intervening in rotated subspaces, then rotating back.
Parallelismmethod0.761
Attribute: an attempt at dualism and dialogue, running texts alongside each other, but inherently unstable.
Intervention Propagationconcept0.759
Property that additive modifications to activations affect all downstream computations, enabling tractable behavioral control