hypothesis

active

hypothesis:neural-representation-geometry-causally-shapes-behavior-interventions-respecting-that-geometry-will-yield-natural-trajectories

Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.

Central hypothesis tested via manifold steering experiments across language models and video world models.

Source paper

extracted_from

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior

(2026) · Daniel Wurgaft · Can Rager · Matthew Kowal · Vasudev Shyam +12

Neighborhood — ranked by edge-count

Findings (2)

finding

Interventions along activation manifold M_h yield behavioral trajectories following behavior manifold M_y, and vice versa — bidirectional relationship demonstrated across language models and video world models.
supports
Central empirical result showing causal coupling between representation and behavior geometry across multiple substrates and modalities.
Optimizing interventions in activation space to produce paths along M_y recovers activation trajectories that trace the curvature of M_h.
supports
Demonstrates bidirectional causal link: behavior manifold geometry can be recovered by optimizing in representation space.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Neural representations carry rich geometric structure; but does that structure causally shape behavior?quote0.882
Opening sentence framing the paper's core inquiry.
Geometric structure of neural representations causally shapes model behaviorclaim0.870
The paper's core causal assertion: geometry is not incidental but mechanistically linked to behavior
Representation geometry causally shapes behavior; activation and behavior manifolds are approximately isometric.claim0.869
Does the geometric structure of neural representations causally shape model behavior?question0.868
The motivating research question of the paper
"Representation geometry is a window into the inner world of neural networks."quote0.846
The paper's concluding summary statement asserting the deep interpretive significance of representation geometry.
The geometry of internal representations and the geometry of model behavior share a precise correspondence — representation geometry is a window into the inner world of neural networks.claim0.845
The paper's deepest interpretive claim, asserting that representation structure and behavioral structure are not coincidentally aligned but deeply connected.
causal shaping of behavior by representation geometryconcept0.844
Central question: does geometry in activation space causally determine behavior?
Geometry in neural representation is not merely incidental, but is in fact the proper object for enabling principled control via intervention on internals.claim0.842
Core interpretive assertion: geometric structure is causally load-bearing, not epiphenomenal.