Path Patching

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Activation patchingmethod0.805
  Standard method in mechanistic interpretability that intervenes on activations; VPD flips this paradigm by patching parameters.
• Path Expansion Methodmethod0.788
  The core analytical technique of expanding transformer computations from layer-by-layer products into sums of end-to-end path terms for independent analysis
• Patch-Closureconcept0.778
  A set property meaning all coordinate patches of its elements remain within the set; proved equivalent to axis-aligned hyperrectangles
• Path Integrationconcept0.776
  Neural mechanism for tracking location through accumulation of self-movement vectors; shown to play the role of position encodings in TEM.
• care pathconcept0.768
  A trajectory through time and space that an agent's care follows, potentially becoming infinite via the bodhisattva vow.
• Path Expansion Trickconcept0.766
  The mathematical trick of expanding a product of layer terms into a sum of end-to-end path terms, enabling independent analysis of each term
• Behavior-based Pathconcept0.765
  The path in activation space derived by optimizing steering interventions to produce outputs along the behavior manifold, independent of representation geometry.
• Patchscopesframework0.764
  Unifying framework for inspecting hidden representations of language models via representation interventions