method
active
method:probing

Probing

Standard interpretability technique used to read feature beliefs.

Neighborhood — ranked by edge-count

Frameworks (1)

framework

Methods (4)

method
  • Attention probe predicting whether an Entity is hallucinated; AUC .94 on validation.
  • Earlier interpretability method applying classifiers to DNN hidden representations; shares complexity-accuracy dilemma with causal abstraction
  • Probing Methods
    related_to
    Top-down interpretability approach studying linguistic properties at various residual stream stages; contrasted with the paper's bottom-up mechanistic approach
  • Probe architecture with a learned query per head for span-level prediction.

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.

  • Probesconcept0.892
    Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
  • Activation Probingconcept0.844
    Technique of reading out model beliefs from internal activations before the final answer token is generated
  • Sparse Probingmethod0.836
    Method from Gurnee et al. 2023 for finding feature directions including individual neuron analysis
  • Probing approach avoiding supervision to sidestep complexity-accuracy tradeoff
  • Causal transformer probe predicting whether a token is in the same Entity as its predecessor.
  • Probe scoreconcept0.807
    Dot product between hidden state and concept vector averaged across 5-layer window around best layer; measures model's internal emotive state
  • Amnesic Probingmethod0.807
    Behavioral explanation technique using amnesic counterfactuals by Elazar et al. 2020
  • Linear Probingmethod0.806
    Used to evaluate representation quality across VTAB tasks