concept
active
concept:probe-scoreProbe score
Dot product between hidden state and concept vector averaged across 5-layer window around best layer; measures model's internal emotive state
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Previous-turn probe scoreextendsInternal state measured at the turn BEFORE the self-report question is appended; ensures measurement of spontaneous internal state uncontaminated by rating question
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.
- Attention probe predicting whether an Entity is hallucinated; AUC .94 on validation.
- Standard interpretability technique used to read feature beliefs.
- LLM judge classification accuracy measuring interpretability; threshold 0.8.
- Test-time compute scaling guided by reward probes with majority-vote over action.
- Prior metric on synthetic repeated random strings; induction score analogous.
- Primary metric for all benchmarks, measuring fraction of tasks that meet benchmark-specific pass criteria
- Joint firing raises TPR at slightly higher FPR.