claim

active

claim:there-is-a-clear-bidirectional-relationship-between-the-geometry-of-behavior-and-representation-steering-along-representation-manifolds-follows-behavior-manifolds-and-vice-versa

There is a clear bidirectional relationship between the geometry of behavior and representation: steering along representation manifolds follows behavior manifolds, and vice versa.

The paper's finding that the alignment holds in both directions — from representation to behavior and from behavior back to representation space.

Source paper

extracted_from

Steering Along Manifolds to Control Neural Networks

Neighborhood — ranked by edge-count

Papers (1)

paper

Steering Along Manifolds to Control Neural Networks
introduces

Findings (1)

finding

The representation-based path and the behavior-based path in Llama-3.1 8B activation space trace out similar curves, demonstrating bidirectional geometry alignment.
supports
Key empirical result showing that optimizing for behavioral outputs and fitting representation geometry produce the same path in activation space.

Claims (2)

claim

There is a bidirectional relationship between the geometry of representation and behavior across tasks and modalities.
restates
Author’s interpretive claim that the shared geometry is general and robust.
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.
extends
The paper's deepest interpretive claim, asserting that representation structure and behavioral structure are not coincidentally aligned but deeply connected.

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 and behavior geometry are bidirectionally alignedclaim0.889
Core finding: the structure models use internally (representations) is precisely reflected in their external behavior (outputs).
Representation geometry causally shapes behavior; activation and behavior manifolds are approximately isometric.claim0.876
bidirectional relationship between representation and behavior geometryconcept0.873
The finding that steering along M_h yields M_y behavior, and optimizing for M_y paths recovers M_h trajectories.
There exists a bidirectional relationship between the geometry of neural representation and the geometry of model behaviorclaim0.863
Central empirical claim of the paper, demonstrated across tasks and modalities
The alignment between representation geometry and behavior geometry is not limited to days of the week but extends to months, letters, ages, and synthetic in-context learning tasks.claim0.854
The paper's generalization claim, asserting that the days-of-week finding scales to other cyclic and structured concepts.
Manifold steering demonstrates bidirectional geometry-behavior link in a video world model on tasks with geometry corresponding to physical dynamicsfinding0.850
Extension of manifold steering validation to video world models and physical dynamics tasks, demonstrating cross-modal generality
We hypothesize that representation geometry drives model behavior — the geometric structure of internal representations causally shapes what models do externally.hypothesis0.849
The causal hypothesis motivating the use of causality (intervention) as the lens connecting representation and behavior geometry.
The analogous circular structure between representation manifold and behavior manifold is downstream of training data and its implicit cyclic conceptual structure.claim0.840
The paper's causal explanation for why representation and behavior geometry both appear circular for days of the week.

Restated by (1)

cosine ≥ 0.90

Other entities that say roughly the same thing. May be merge candidates or independent restatements across papers.

claim
There is a bidirectional relationship between the geometry of representation and behavior across tasks and modalities.