The relationship between the brain and transformers is close because of a mathematical relationship between models, not merely because of shared neural representations

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

• There exists a bidirectional relationship between the geometry of neural representation and the geometry of model behaviorclaim0.797
  Central empirical claim of the paper, demonstrated across tasks and modalities
• Neural networks show substantial alignment with biological representations in the brain, driven by shared task and data constraintsclaim0.792
  Extends convergence argument to brain-machine alignment
• The huge chemical complexity within each synapse suggests that neural models of cognition that refer only to changing weights of synaptic connections and ignore sub-neural chemistry are probably ignoring some of the most important explanatory mechanisms in brains.claim0.786
  Sloman's critique of mainstream neural network theories.
• Different neural network models trained on different objectives and modalities are converging to a shared statistical model of reality in their representation spaceshypothesis0.782
  The central hypothesis of the paper; the platonic representation hypothesis itself
• The ability to represent relationships (e.g. correlations or associations) among variables, rather than a system of independent variables, is essential for any connectionist model of cognition.claim0.782
  Necessary condition for connectionist cognition.
• The conservation of molecular mechanisms between neural and non-neural bioelectricity is why neuroscience tools work everywhere in the body.claim0.776
  Empirical claim about transferability of methods.
• There is a bidirectional relationship between the geometry of representation and behavior across tasks and modalities.claim0.765
  Author’s interpretive claim that the shared geometry is general and robust.
• We hypothesize that potential 'consciousness' phenomena are preferentially associated with deeper transformer layers and the 2/3 layer of LLMs.hypothesis0.763
  Derived from observed alignment of promising cases with semantically rich deeper layers and the brain-aligned 2/3 layer.