manifold learning

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• manifoldconcept0.845
  A smooth, potentially curved surface in activation space along which activations vary according to a coherent semantic dimension.
• manifold geometry principles extend to months, letters, ages, and in-context learning tasks across modalitiesfinding0.795
  Evidence that the weekday cyclic structure is not anomalous but reflects broader principle of concept geometry.
• behavior manifoldconcept0.784
  One-dimensional curved surface in output probability space; the paper shows this mirrors representation manifold structure.
• manifold-level descriptionconcept0.776
  An interpretability approach that describes representations in terms of entire curved manifolds rather than many small features.
• One-dimensional Manifoldconcept0.771
  The type of manifold fitted to the cyclic concept structure in both activation and behavior space — a path along which steering moves the model.
• Feature Manifoldsframework0.771
  Hypothesized extension of superposition where features may be higher-dimensional manifolds rather than 1D directions
• Manifold geometry provides a practical blueprint for steering model behavior across diverse tasks and modalities.hypothesis0.769
  The generalizing predictive claim that manifold steering is a broadly applicable framework beyond the days-of-week case study.
• representation manifoldconcept0.769
  One-dimensional curved surface in internal activation space; the paper demonstrates alignment with behavior manifold.