method
active
method:interchange-intervention-training-objectiveInterchange Intervention Training Objective
Differentiable training objective minimized when a high-level model is an abstraction of a neural network under a given alignment.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- 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.
- Fundamental operation for causal abstraction analysis; forces neurons to take values from source inputs to create counterfactuals.
- Training technique that induces specific causal structures in neural networks by co-training with interchange interventions
- Proportion of aligned interchange interventions with equivalent high-level and low-level effects; graded measure of causal abstraction.
- Extends interchange interventions to non-standard bases by rotating representations, intervening in rotated subspaces, then rotating back.
- Evaluation metric measuring how well a trained intervention matches desired counterfactual model behavior
- Metric measuring accuracy of DNN under intervention at matching algorithm-predicted outputs on held-out test set
- Full n-dimensional activation replacement; most expressive intervention tested, used as upper bound in appendix