claim
active
claim:the-core-problem-of-steering-should-be-recast-from-finding-the-right-direction-to-finding-the-right-geometryThe core problem of steering should be recast from finding the right direction to finding the right geometry
The paper's programmatic conclusion about how the field should reconceptualize neural network steering
Source paper
extracted_from(2026) · Daniel Wurgaft · Can Rager · Matthew Kowal · Vasudev Shyam +12
Neighborhood — ranked by edge-count
Papers (1)
paper
Communities (3)
community
- Explores geometry of activation/behavior manifolds to enable selective, non-destructive concept interventions.
- Concepts encoded as curved manifolds and circular structures in LLM activation spaces.
- Framework treating teleonomic behavior and goal-directedness as geometric alignment problems across anatomical, physiological, and representational spaces; emphasizes intervention via internal geometry rather than external direction.
Claims (1)
claim
- Core interpretive assertion: geometric structure is causally load-bearing, not epiphenomenal.
Questions (1)
question
- The reframed steering problem the paper introduces
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.
- Core mechanism statement.
- The paper's critique of the standard linear steering baseline, supported by the days-of-week demo.
- Positions the contribution relative to Angular Steering and Dynamic Steering literature
- Suggests localization.
- Demonstration of steering reasoning length.
- Linear steering implicitly assumes a flat, Euclidean activation space, leading to off-manifold excursions.
- General technique of modifying activations to control model behavior.