method
active
method:probingProbing
Standard interpretability technique used to read feature beliefs.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Core pipeline turning probe-read features into scalable reward functions for open-ended tasks.
Methods (4)
method
- Classification proberelated_toAttention probe predicting whether an Entity is hallucinated; AUC .94 on validation.
- Diagnostic Probingrelated_toEarlier interpretability method applying classifiers to DNN hidden representations; shares complexity-accuracy dilemma with causal abstraction
- Probing Methodsrelated_toTop-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 edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
- Technique of reading out model beliefs from internal activations before the final answer token is generated
- 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.
- Dot product between hidden state and concept vector averaged across 5-layer window around best layer; measures model's internal emotive state
- Behavioral explanation technique using amnesic counterfactuals by Elazar et al. 2020
- Used to evaluate representation quality across VTAB tasks