Fourier features

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

• Geometry of featuresconcept0.799
  Research thread within About Blank concerning the structure and relational properties of neural network feature representations; covariance pooling tangentially supports this thread.
• The Fourier feature periods (2, 5, 10) respect standard base-10 addition structure rather than cyclic concept periodicityclaim0.784
  Mechanistic claim linking identified Fourier features to base-10 arithmetic
• Fourier features with period 10 contribute to base-10 sum computation in the 28-neuron clusterfinding0.746
  One of the three base-10 Fourier periods identified in the sparse neuron set
• atomic featuresconcept0.743
  The idea that interpretability should decompose representations into minimal, indivisible feature units; contrasted with manifold-level descriptions.
• Feature Sparsityconcept0.741
  Property that features activate on only a small fraction of inputs; enables compressed sensing and is what allows superposition to work
• Linear Representation of Featuresconcept0.735
  The central object of study — the idea that a concept like truth is encoded as a direction in the LLM's latent space
• Feature Manifoldsframework0.734
  Hypothesized extension of superposition where features may be higher-dimensional manifolds rather than 1D directions
• Feature Density Histogrammethod0.728
  Log-scale histogram of feature firing rates used as proxy for autoencoder quality during hyperparameter tuning