concept
active
concept:serializable-intervention

Serializable Intervention

pyvene's approach of storing interventions as shareable serialized objects rather than runtime code

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Intervention mode where interventions are applied sequentially, each building on the previous one

Artifacts (1)

artifact
  • Public model hub through which pyvene-intervened models can be shared via serialization

Related by similarity (8)

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.

  • Intervention targeting specific dimensional subsets of activation vectors rather than full representations
  • Property that additive modifications to activations affect all downstream computations, enabling tractable behavioral control
  • Intervention mode where multiple interventions are applied simultaneously to the same base computation graph
  • Manipulation of activations along a straight line; shown to fail when it crosses voids, in contrast to manifold-following interventions.
  • Perturbing source features along decoder direction and measuring target change.
  • Fundamental operation for causal abstraction analysis; forces neurons to take values from source inputs to create counterfactuals.
  • The use of interventions (rather than correlations) to establish a causal link between representation geometry and behavioral geometry.
  • Modifying SAE hidden activations h to h-tilde while keeping error term fixed, then continuing inference.