question
active
question:what-mechanisms-underlie-the-changes-to-the-policy-including-the-reduction-when-interventions-are-inlinedWhat mechanisms underlie the changes to the policy, including the reduction when interventions are inlined?
Open interpretability question.
Source paper
extracted_from(2026) · Aaditya Vikram Prasad · Connor Watts · Jack Merullo · Dhruvil Gala +3
Neighborhood — ranked by edge-count
Papers (1)
paper
- Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretabilityassociated_withmentions
Hypotheses (1)
hypothesis
- Mechanism hypothesis for future work.
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.
- Train-time scaling.
- Decomposition component.
- Additional synthetic example of pernicious divergence from balanced subspaces
- 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
- Practical implication.
- Feature interventions generated meaningful model output changes while minimizing performance degradationfinding0.749Listed achievement in TL;DR.
- Modifying SAE hidden activations h to h-tilde while keeping error term fixed, then continuing inference.
- The goal of mechanistically-grounded, reliable control of neural network behavior via activation interventions