method
active
method:amnesic-probing

Amnesic Probing

Behavioral explanation technique using amnesic counterfactuals by Elazar et al. 2020

Neighborhood — ranked by edge-count

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.

  • Probingmethod0.807
    Standard interpretability technique used to read feature beliefs.
  • Earlier interpretability method applying classifiers to DNN hidden representations; shares complexity-accuracy dilemma with causal abstraction
  • Probing Methodsmethod0.772
    Top-down interpretability approach studying linguistic properties at various residual stream stages; contrasted with the paper's bottom-up mechanistic approach
  • Activation Probingconcept0.767
    Technique of reading out model beliefs from internal activations before the final answer token is generated
  • Attention probe predicting whether an Entity is hallucinated; AUC .94 on validation.
  • Probesconcept0.763
    Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
  • Probing approach avoiding supervision to sidestep complexity-accuracy tradeoff
  • Causal transformer probe predicting whether a token is in the same Entity as its predecessor.