claim

active

claim:there-exists-a-bidirectional-relationship-between-the-geometry-of-neural-representation-and-the-geometry-of-model-behavior

There exists a bidirectional relationship between the geometry of neural representation and the geometry of model behavior

Central empirical claim of the paper, demonstrated across tasks and modalities

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

Papers (1)

paper

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

Findings (3)

finding

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.
Steering along M_h yields behavioral trajectories that follow M_y, producing more natural outputs than linear steering
supports
Core empirical result demonstrating the superiority of manifold steering over linear steering
Manifold steering demonstrates bidirectional geometry-behavior link in a video world model on tasks with geometry corresponding to physical dynamics
supports
Extension of manifold steering validation to video world models and physical dynamics tasks, demonstrating cross-modal generality

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.

There is a bidirectional relationship between the geometry of representation and behavior across tasks and modalities.claim0.888
Author’s interpretive claim that the shared geometry is general and robust.
bidirectional relationship between representation and behavior geometryconcept0.885
The finding that steering along M_h yields M_y behavior, and optimizing for M_y paths recovers M_h trajectories.
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.claim0.882
The paper's deepest interpretive claim, asserting that representation structure and behavioral structure are not coincidentally aligned but deeply connected.
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
There is a clear bidirectional relationship between the geometry of behavior and representation: steering along representation manifolds follows behavior manifolds, and vice versa.claim0.863
The paper's finding that the alignment holds in both directions — from representation to behavior and from behavior back to representation space.
Does the geometric structure of neural representations causally shape model behavior?question0.860
The motivating research question of the paper
representation geometry and behavior geometry are bidirectionally alignedclaim0.843
Core finding: the structure models use internally (representations) is precisely reflected in their external behavior (outputs).
geometric structure in neural network representations drives model behaviorclaim0.842
Interpretive assertion that representation geometry is not epiphenomenal but causally shapes what models do externally.