Sparse Probing

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

• Probing Methodsmethod0.809
  Top-down interpretability approach studying linguistic properties at various residual stream stages; contrasted with the paper's bottom-up mechanistic approach
• Sparse and smooth codingconcept0.803
  Coding scheme where qualities are represented by few neurons with continuous similarity relations.
• Probesconcept0.794
  Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
• Unsupervised Probingmethod0.792
  Probing approach avoiding supervision to sidestep complexity-accuracy tradeoff
• Activation Probingconcept0.782
  Technique of reading out model beliefs from internal activations before the final answer token is generated
• Diagnostic Probingmethod0.776
  Earlier interpretability method applying classifiers to DNN hidden representations; shares complexity-accuracy dilemma with causal abstraction
• Sparse Feature Dictionaryconcept0.766
  The extracted set of sparse interpretable features from model embeddings via SAEs
• Sparse circuitsconcept0.754
  A goal in mechanistic interpretability to identify sparse computational subgraphs; VPD promotes sparse parameter circuits.