A Mathematical Framework for Transformer Circuits (Elhage et al., 2021)

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

• A Mathematical Framework for Transformer Circuitsframework0.939
  Prior Anthropic paper enabling circuit-level analysis of attention-only transformers; motivates current MLP decomposition
• Circuits Frameworkframework0.787
  Mechanistic interpretability framework for understanding neural network computation as circuits of features
• Learning to encode position for transformer with continuous dynamical model (Liu et al., 2020)concept0.769
  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.claim0.760
  Janus's interpretive framing of transformers as causal graphs.
• transformer architectureframework0.757
  Neural network architecture based on attention, commonly used in large language models
• Transformers use an anti-Markovian solution that recomputes relevant numeric information at each step in the Multi-Object taskclaim0.750
  Prior finding from Grant et al. 2025 used to interpret low MAS IIA for GRU-Transformer hidden state comparisons.
• The transformer entity is tricameral (base simulator, simulated simulator, simulated awareness), but there is less discreteness between these layers than previously claimed.claim0.747
  Antra's revision of her earlier model; still considers interference between levels important.
• Transformer decoder architectureframework0.742
  Base architecture of reasoning LLMs studied, with attention and MLP blocks per layer