hypothesis
active
hypothesis:if-the-relationship-is-present-in-activations-better-tools-e-g-trained-on-these-datasets-could-surface-itIf the relationship is present in activations, better tools (e.g. trained on these datasets) could surface it
Alternative explanation.
Source paper
extracted_from(2026) · Adam Karvonen · Euan Ong · Subhash Kantamneni · Samuel Marks
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- No activation tool (AO, NLA, SAE) improves on transcript-only baseline for Gemma-3-27B-IT targetassociated_withMain negative result; baseline AUROC ~81 with tools within ~1 point.
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.
- Asserts that organismic identity is fundamentally a cognitive structure.
- Further studying the relation between activation probes and the logit monitor could help better understand activation probeshypothesis0.793Future work.
- Motivates shift from studying model activations ('thoughts') to understanding parameters ('the computations themselves').
- Discovery claim.
- Mechanism by which activation of an emotion feature sometimes leads to later suppression of that same featurequestion0.786Identified research gap: the paper observes anti-persistence but has no explanation for it
- Stated limitation.
- Motivates nested SAE.
- Practical implication.