method
active
method:distributed-interchange-interventionDistributed Interchange Intervention
Extends interchange interventions to non-standard bases by rotating representations, intervening in rotated subspaces, then rotating back.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Orthogonal Decomposition of Representation Spaceassociated_withMathematical structure central to distributed interchange interventions; representation space decomposed into orthogonal subspaces each aligned with a high-level variable.
Methods (3)
method
- Interchange Interventionextendsrelated_toFundamental operation for causal abstraction analysis; forces neurons to take values from source inputs to create counterfactuals.
- Core intervention method used throughout CausalGym; operates on one-dimensional non-basis-aligned subspace of activation space
- The core method introduced in this paper: finds alignments between high-level causal variables and distributed neural representations via gradient descent.
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.
- Proportion of aligned interchange interventions with equivalent high-level and low-level effects; graded measure of causal abstraction.
- Differentiable training objective minimized when a high-level model is an abstraction of a neural network under a given alignment.
- Full n-dimensional activation replacement; most expressive intervention tested, used as upper bound in appendix
- Intervention mode where multiple interventions are applied simultaneously to the same base computation graph
- Training technique that induces specific causal structures in neural networks by co-training with interchange interventions
- Evaluation metric measuring how well a trained intervention matches desired counterfactual model behavior
- Property that additive modifications to activations affect all downstream computations, enabling tractable behavioral control
- Intervention targeting specific dimensional subsets of activation vectors rather than full representations