method
active
method:attribution-patching-atp

Attribution patching / AtP*

Gradient-based approximation to activation patching.

Neighborhood — ranked by edge-count

Methods (2)

method

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.

  • Used by prior work to identify consistency heads.
  • Measure causal importance of upstream variables.
  • Standard method in mechanistic interpretability that intervenes on activations; VPD flips this paradigm by patching parameters.
  • Data Attributionconcept0.756
    The task of attributing model behaviors to specific training datapoints.
  • Gradient-based technique using SAE features to estimate causal effects on completions; used to corroborate NLA findings.
  • Correlating attribution vectors (feature activation × logit weight of next token) across model pairs to measure functional universality
  • Path Patchingmethod0.744
    Method by Goldowsky-Dill et al. 2023 for localizing model behavior via targeted activation interventions