question
active
question:how-do-llm-computations-process-and-transform-these-activationsHow do LLM computations process and transform these activations?
Mechanistic question AOs can't answer.
Source paper
extracted_from(2025) · Adam Karvonen
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Defines scope; they cannot answer encoding, geometry, or algorithm questions.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Emotion emerges early, peaks in middle layers, sharpens with scale, and persists across tokens in LLM activations per Zhang & Zhong 2025
- Sharma et al. result supporting cross-modal alignment: language-only models implicitly encode visual structure
- Time-dependent correlation structure in activations.
- The finding that interpretable concepts including character traits are encoded as linear directions in transformer residual streams
- Motivates shift from studying model activations ('thoughts') to understanding parameters ('the computations themselves').
- Qualified positive claim from spatio permutation analysis where two cases satisfy all three criteria.
- Autocorrelation of LM activations varies with sequence position, unlike the stationary surrogate.finding0.728Fig. 2b,f.
- Supporting evidence for cross-modal platonic representation