The transformer entity is tricameral (base simulator, simulated simulator, simulated awareness), but there is less discreteness between these layers than previously claimed.

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

• It's tricky, because for a typical language model the entity is sort of tricameral: the base simulator, the simulated simulator, and the simulated awareness.quote0.855
  Antra's earlier definitive statement of the tricameral model.
• Transformer cognition operates via interference patterns across redundant paths, encoding nuanced state deltas similar to continuous human memory.claim0.768
  Proposes transformers experience cognition as interference-based and continuous; connects to Anima Labs reports of parallel processing.
• Different introspective tasks may preferentially use different path distributions in the transformer.claim0.759
  Interpretive claim connecting exponential path combinatorics to Lindsey's layer-dependent findings.
• Sequences of contemporary Transformer-based LLM representations lack statistically significant indicators of observed 'consciousness' phenomena under the three stringent criteria.claim0.757
  Primary conclusion of the study based on temporal permutation analysis failing all three criteria.
• Learning to encode position for transformer with continuous dynamical model (Liu et al., 2020)concept0.752
  Prior work on learned dynamic position encodings; cited alongside Wang et al. as precedent.
• Transformer can be viewed as a Wolfram causal graph with foliations specifying computation order.claim0.751
  Janus's interpretive framing of transformers as causal graphs.
• The underlying simulator has no agency of its own, not even in a mimetic sense, nor beliefs, preferences or goalsclaim0.748
  Distinguishes the passive simulator from active simulacra that can appear to have agency
• A Mathematical Framework for Transformer Circuits (Elhage et al., 2021)concept0.747
  Foundational mechanistic interpretability paper on transformer circuit analysis