finding

active

finding:optimizing-interventions-in-activation-space-to-produce-paths-along-m-y-recovers-activation-trajectories-that-trace-the-curvature-of-m-h

Optimizing interventions in activation space to produce paths along M_y recovers activation trajectories that trace the curvature of M_h.

Demonstrates bidirectional causal link: behavior manifold geometry can be recovered by optimizing in representation space.

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

Claims (2)

claim

There is a bidirectional relationship between the geometry of representation and behavior across tasks and modalities.
supports
Author’s interpretive claim that the shared geometry is general and robust.
There exists a bidirectional relationship between the geometry of neural representation and the geometry of model behavior
supports
Central empirical claim of the paper, demonstrated across tasks and modalities

Hypotheses (1)

hypothesis

Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.
supports
Central hypothesis tested via manifold steering experiments across 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.
Manifold isometry between representations and behavior
members_of
Neural network activation and behavior manifolds maintain geometric correspondence, enabling intervention optimization across language models and vision tasks.

Methods (1)

method

Behavior-Optimized Activation Path Recovery
supports
Method of optimizing activation-space interventions to produce behavioral paths along M_y, then measuring whether the resulting activation trajectories trace M_h curvature

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.

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.finding0.853
Central empirical result showing causal coupling between representation and behavior geometry across multiple substrates and modalities.
We hypothesize that interventions that respect the geometry of activation space will yield behaviors close to those the model exhibits naturallyhypothesis0.828
The core testable hypothesis driving the experimental design
Linear interventions across voids in activation space produce incoherent output, while following the manifold curve produces smooth control.claim0.823
General principle derived from the Mountain Car experiment: curved manifold-following yields coherent manipulation, linear shortcuts fail.
optimization of interventions to follow behavior manifold M_ymethod0.814
Method that optimizes activation interventions so that resulting behaviors trace M_y, recovering activation paths that follow M_h curvature.
The representation-based path and the behavior-based path in Llama-3.1 8B activation space trace out similar curves, demonstrating bidirectional geometry alignment.finding0.787
Key empirical result showing that optimizing for behavioral outputs and fitting representation geometry produce the same path in activation space.
MCA creates a more tractable search space by smoothing the fitness landscape, mitigating the inverse problem and enabling survival of mutations that would otherwise be deleterious.claim0.773
Subclaim.
Faster-converging trajectories take direct PCA-space paths to the true solution; slower trajectories take indirect routes visiting saddle pointsfinding0.765
PCA-space visualization linking route geometry to convergence speed.
Representation geometry causally shapes behavior; activation and behavior manifolds are approximately isometric.claim0.765