concept
active
concept:present-speaker-and-other-speaker-probesPresent speaker and other speaker probes
Distinct representations for the operative emotion of the current versus the other speaker.
Neighborhood — ranked by edge-count
Papers (1)
paper
Datasets (1)
dataset
- Dialogues with independently specified emotions for two speakers.
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.
- Two separate representations.
- Other-speaker probes may encode the present speaker's reaction, enabling emotional regulation circuitshypothesis0.808Part 2 and appendix.
- 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.
- Causal transformer probe predicting whether a token is in the same Entity as its predecessor.
- Representations not tied to Assistant.
- Top-down interpretability approach studying linguistic properties at various residual stream stages; contrasted with the paper's bottom-up mechanistic approach