claim

active

claim:geometry-in-neural-representation-is-not-merely-incidental-but-is-in-fact-the-proper-object-for-enabling-principled-control-via-intervention-on-internals

Geometry in neural representation is not merely incidental, but is in fact the proper object for enabling principled control via intervention on internals.

Core interpretive assertion: geometric structure is causally load-bearing, not epiphenomenal.

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 (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.
Cross-task and cross-modal validation of manifold steering
supports
The paper demonstrates the bidirectional geometry-behavior relationship across multiple tasks and modalities (language models and video world models)

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.
Geometric goal-alignment in multi-scale systems
members_of
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.

Concepts (1)

concept

principled control via internals using geometry
supports
Claim that geometry enables accurate intervention; steering moves from direction-finding to geometry-finding.

Questions (2)

question

Does the geometric structure of neural representations causally shape model behavior?
gates
The motivating research question of the paper
Does the geometric structure of activation space causally shape neural network behavior?
gates
Central research question driving the work.

Claims (1)

claim

The core problem of steering should be recast from finding the right direction to finding the right geometry
extends
The paper's programmatic conclusion about how the field should reconceptualize neural network steering

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.

"Representation geometry is a window into the inner world of neural networks."quote0.862
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.claim0.849
The paper's deepest interpretive claim, asserting that representation structure and behavioral structure are not coincidentally aligned but deeply connected.
Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.842
Central hypothesis tested via manifold steering experiments across language models and video world models.
Neural representations carry rich geometric structure; but does that structure causally shape behavior?quote0.805
Opening sentence framing the paper's core inquiry.
"Concept geometry provides a blueprint for controlling the behavior of neural networks—if you know how to look."quote0.802
The opening statement of the paper, framing concept geometry as the key to neural network control.
We hypothesize that representation geometry drives model behavior — the geometric structure of internal representations causally shapes what models do externally.hypothesis0.802
The causal hypothesis motivating the use of causality (intervention) as the lens connecting representation and behavior geometry.
There is a bidirectional relationship between the geometry of representation and behavior across tasks and modalities.claim0.801
Author’s interpretive claim that the shared geometry is general and robust.
Representation geometry causally shapes behavior; activation and behavior manifolds are approximately isometric.claim0.797