claim

active

claim:geometric-structure-of-neural-representations-causally-shapes-model-behavior

Geometric structure of neural representations causally shapes model behavior

The paper's core causal assertion: geometry is not incidental but mechanistically linked to behavior

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 (1)

finding

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

Communities (3)

community

Manifold-aware concept steering in neural representations
members_of
Explores geometry of activation/behavior manifolds to enable selective, non-destructive concept interventions.
Geometric concept representations in neural networks
members_of
Concepts encoded as curved manifolds and circular structures in LLM activation spaces.
Neural geometry as fundamental computational substrate
members_of
Geometric structure in neural representations causally determines computation and behavior across diverse architectures, revealed through analysis of learned manifolds and cyclic concepts.

Questions (2)

question

Does the geometric structure of neural representations causally shape model behavior?
gates
The motivating research question of the paper
does that structure causally shape behavior?
gates
Opening question: does the rich geometric structure of neural representations have a causal role in behavior?

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?quote0.904
Opening sentence framing the paper's core inquiry.
geometric structure in neural network representations drives model behaviorclaim0.885
Interpretive assertion that representation geometry is not epiphenomenal but causally shapes what models do externally.
Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.870
Central hypothesis tested via manifold steering experiments across language models and video world models.
There exists a bidirectional relationship between the geometry of neural representation and the geometry of model behaviorclaim0.870
Central empirical claim of the paper, demonstrated across tasks and modalities
We hypothesize that representation geometry drives model behavior — the geometric structure of internal representations causally shapes what models do externally.hypothesis0.858
The causal hypothesis motivating the use of causality (intervention) as the lens connecting representation and behavior geometry.
How does representation geometry causally drive model behavior?question0.844
The central scientific question the paper addresses through the lens of interventional causality.
Does the geometric structure of activation space causally shape neural network behavior?question0.843
Central research question driving the work.
causal shaping of behavior by representation geometryconcept0.836
Central question: does geometry in activation space causally determine behavior?