Transformer decoder architecture

Base architecture of reasoning LLMs studied, with attention and MLP blocks per layer

Neighborhood — ranked by edge-count

concept

Latent-Space Representations
associated_with
Substrate on which causal emergence was computed across agent lifetimes; aligned with learning success.

cosine ≥ 0.65 · no typed edge

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

transformer architectureframework0.846
Neural network architecture based on attention, commonly used in large language models
Decoder-only transformer architectures are fundamentally limited in generating long, coherent sequences due to lack of ordered phase.claim0.801
Interpretation of Proposition 2 as a fundamental limitation on LLMs
Decision Transformermethod0.749
A model that frames RL as sequence modeling, SOTA from random trajectories.
Spectral Decodermethod0.746
Method that maps latent concept steering interventions back to EEG amplitude spectrum to obtain physiologically interpretable frequency signatures.
A Mathematical Framework for Transformer Circuits (Elhage et al., 2021)concept0.742
Foundational mechanistic interpretability paper on transformer circuit analysis
A Mathematical Framework for Transformer Circuitsframework0.739
Prior Anthropic paper enabling circuit-level analysis of attention-only transformers; motivates current MLP decomposition
Signal Transformerconcept0.734
Core abstraction in Fruit: pure function mapping signals to signals; enables compositional GUI definitions.
Transformer Neural Networkframework0.733
Core machine learning architecture analyzed in the paper; shown to be mathematically related to TEM.