concept
active
concept:serial-interventionSerial Intervention
Intervention mode where interventions are applied sequentially, each building on the previous one
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (2)
concept
- Serializable Interventionrelated_topyvene's approach of storing interventions as shareable serialized objects rather than runtime code
- Neural Network InterventionextendsThe fundamental operation of making in-place changes to model activations, placing the model in a counterfactual state
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.
- Intervention mode where multiple interventions are applied simultaneously to the same base computation graph
- 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
- Manipulation of activations along a straight line; shown to fail when it crosses voids, in contrast to manifold-following interventions.
- Fundamental operation for causal abstraction analysis; forces neurons to take values from source inputs to create counterfactuals.
- Extends interchange interventions to non-standard bases by rotating representations, intervening in rotated subspaces, then rotating back.
- The use of interventions (rather than correlations) to establish a causal link between representation geometry and behavioral geometry.
- Scalar parameter modulating how strongly a steering vector shifts model activations; set to 15 for Exp1 and ±16 for Exp2