method
active
method:l-importance-minimality-loss

L_importance-minimality loss

Penalizes causal importance values above 0 with p-norm; works with p>1.

Neighborhood — ranked by edge-count

Papers (1)

paper

Frameworks (1)

framework

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.

  • Loss on randomly masked subcomponents matching target outputs, with layerwise auxiliary.
  • L_retain Loss Termconcept0.727
    Regularization component of the composite loss that penalizes deviation from baseline model behavior on Alpaca instructions
  • Distance-based loss comparing injected representation to class centroids in the active subspace
  • Auxiliary training objective from Grant (2025) that constrains intervened representations to remain near natural distribution
  • Loss function pulling representations toward positive centroid and pushing away from negative centroid with angular margins
  • Prior state-of-the-art baseline using the abliterated model as proposal distribution.
  • Causal importanceconcept0.706
    A measure of whether a subcomponent is necessary to reproduce model behavior on a specific prompt, predicted by the causal importance network.
  • Small per-subcomponent MLP with hard sigmoid predicting causal importance.