hypothesis
active
hypothesis:scaling-causal-interventions-on-codes-will-move-from-qualitative-alignment-to-mechanistic-claimsScaling causal interventions on codes will move from qualitative alignment to mechanistic claims.
Future work.
Source paper
extracted_from(2025) · Lubana, Ekdeep Singh · Rager, Can · Hindupur, Sai Sumedh R. · Costa, Valerie +12
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Representational dynamics of causal emergence align with reward improvement in most tasks.finding0.784The trajectory of causal emergence through training mirrors the reward improvement curve across the majority of tested environments.
- Authors connect their finding to the prior probing literature debate
- Downside of abstraction.
- The use of interventions (rather than correlations) to establish a causal link between representation geometry and behavioral geometry.
- Call to extend the inference of sentience to non-biological systems as well.
- Method of shifting hidden state activations along probe directions to cause the model to treat false statements as true and vice versa; evaluated on OOD inputs
- Asserts that the time is ripe for formal models.