method
active
method:classification-probe

Classification probe

Attention probe predicting whether an Entity is hallucinated; AUC .94 on validation.

Neighborhood — ranked by edge-count

Frameworks (1)

framework

Methods (4)

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.

  • Probesconcept0.894
    Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
  • Earlier interpretability method applying classifiers to DNN hidden representations; shares complexity-accuracy dilemma with causal abstraction
  • Correction probemethod0.834
    Reward probe grading correction interventions (5-class).
  • The ability of probes trained on one dataset to transfer accurately to topically and structurally different datasets
  • Internals-based approach to which the logit monitor is complementary.
  • Probe scoreconcept0.819
    Dot product between hidden state and concept vector averaged across 5-layer window around best layer; measures model's internal emotive state
  • Probing Methodsmethod0.816
    Top-down interpretability approach studying linguistic properties at various residual stream stages; contrasted with the paper's bottom-up mechanistic approach
  • Joint firing raises TPR at slightly higher FPR.