does the transformer genuinely use a local code for token-in-context features, or is dictionary learning producing a local code artifact from a compositional underlying representation?

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

• Transformers develop self-models through in-context learning, not just training data; even old base models without LLM-related text can bootstrap self-referential reasoning at runtime.claim0.776
  Antra's foundational claim about how introspection arises computationally rather than from memorised text.
• Transformers learn in-context by gradient descent, functioning as mesa-optimizers that learn internal models in real timefinding0.771
  Evidence that in-context learning is not mere pattern matching but genuine optimization, relevant to applying the thesis to inference
• The problem isn't that it is a transformer. The problem is that it is an auto-regressive LLM. Auto-regressive LLMs that compute each token with a fixed number of computational steps can't reason, regardless of the details of the architecture.quote0.769
  LeCun's post on X supporting the view that fixed-step probabilistic prediction precludes consciousness in LLMs.
• We hypothesize that a very high number of training tokens may allow the transformer to learn cleaner representations in superpositionhypothesis0.756
  Motivation for heavily overtraining the one-layer transformer on 100 billion tokens
• Transformers almost surely maintain input-injectivity throughout training, not just at initialisationhypothesis0.749
  Conjecture supported by Nikolaou et al. 2025 for last-token hidden states
• Learning to encode position for transformer with continuous dynamical model (Liu et al., 2020)concept0.740
  Prior work on learned dynamic position encodings; cited alongside Wang et al. as precedent.
• Different introspective tasks may preferentially use different path distributions in the transformer.claim0.737
  Interpretive claim connecting exponential path combinatorics to Lindsey's layer-dependent findings.
• Transformer cognition operates via interference patterns across redundant paths, encoding nuanced state deltas similar to continuous human memory.claim0.734
  Proposes transformers experience cognition as interference-based and continuous; connects to Anima Labs reports of parallel processing.