method
active
method:probing-methods

Probing Methods

Top-down interpretability approach studying linguistic properties at various residual stream stages; contrasted with the paper's bottom-up mechanistic approach

Neighborhood — ranked by edge-count

Methods (1)

method
  • Earlier interpretability method applying classifiers to DNN hidden representations; shares complexity-accuracy dilemma with causal abstraction

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.

  • Probesconcept0.826
    Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
  • Activation Probingconcept0.813
    Technique of reading out model beliefs from internal activations before the final answer token is generated
  • Sparse Probingmethod0.809
    Method from Gurnee et al. 2023 for finding feature directions including individual neuron analysis
  • Probing approach avoiding supervision to sidestep complexity-accuracy tradeoff
  • Method of using base models (no post-training) to observe spontaneous self-referential behaviors without confound of memorized introspection language.
  • Linear Probingmethod0.796
    Used to evaluate representation quality across VTAB tasks
  • Amnesic Probingmethod0.772
    Behavioral explanation technique using amnesic counterfactuals by Elazar et al. 2020
  • Marker Methodmethod0.767
    Method for assessing consciousness in nonhuman animals by identifying behavioral/anatomical markers from humans and extrapolating; proposed adaptation for AI.