method
active
method:l-stochastic-recon-lossL_stochastic-recon loss
Loss on randomly masked subcomponents matching target outputs, with layerwise auxiliary.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Linear parameter decomposition with stochastic ablation.
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.
- Regularization component of the composite loss that penalizes deviation from baseline model behavior on Alpaca instructions
- Samples task weights from a standard normal distribution.
- Penalizes causal importance values above 0 with p-norm; works with p>1.
- Reconstruction fidelity score based on cross-entropy.
- Transformers are recurrent through autoregression because the K/V stream provides horizontal information flow across positions, even though each forward pass is feedforward.
- 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
- Auxiliary objective combining L2 and cosine losses against pre-recorded CL vectors to improve causal relevance when one model is causally inaccessible.