SAE Latents

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

• Concreteness Filtering of SAE Latentsconcept0.790
  Pre-filtering step excluding abstract latents where off-topic detection is harder
• Sparse Autoencoders (SAE)method0.782
  Interpretability method criticized in this paper for shattering manifolds into atomic pieces, obscuring overarching semantic structure.
• SAE featuresconcept0.776
  The individual, supposedly monosemantic directions learned by SAEs; argued here to fragment manifolds into disconnected pieces.
• Latent SOO Metricmethod0.756
  Metric measuring the mean MSE between self and other-referencing activations across all hidden MLP/attention layers
• Latent Structuresconcept0.745
  Hidden or underdeveloped structures existing 'between the lines' of a configuration that can be enhanced and developed through harmony-seeking computation.
• latent patternsconcept0.742
  Statistical regularities stored in pretrained models.
• Latent entitiesconcept0.741
  Entities that become visible as centers in a configuration (e.g., rectangles of white space around a dot) that were not present before.
• Backtracking Latentsconcept0.734
  SAE latents that rise as correction approaches and peak after self-correction begins, complementing OTDs