arXiv:2607. 21491v1 Announce Type: cross Abstract: Do independently trained language models come to represent the same thing in the same way?
arXiv:2606. 05378v1 Announce Type: new Abstract: We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families.
arXiv:2606. 00926v1 Announce Type: new Abstract: Mechanistic studies of sequence models often treat layerwise state encodings as architectural traits: recurrent models concentrate readable state, attention-based models distribute it.
arXiv:2608. 01548v1 Announce Type: cross Abstract: Language can be viewed as a formalized subset of thought: a consequence-governed symbolic structure projected from wider situated cognition.
arXiv:2607. 18476v1 Announce Type: cross Abstract: When a language model must choose one answer from a large space of equally valid options, a format clause -- "Reply with JSON only" -- changes which answer it chooses.
arXiv:2608. 05162v1 Announce Type: cross Abstract: Pooling is a consequential but under-examined design choice in decoder-only concept representation work: practitioners must collapse token-level hidden states into a passage-level vector, yet no shared protocol exists for comparing this choice across concepts, models, and tasks.
arXiv:2608. 10420v1 Announce Type: new Abstract: Reasoning shortcuts are solutions of a neurosymbolic system's rules that produce correct predictions through unintended concepts.
arXiv:2607. 24797v1 Announce Type: cross Abstract: In the literate human brain, reading and writing are two doubly-dissociable systems: a ventral decoding route (impaired in pure alexia) and a fronto-parietal encoding route (impaired in pure agraphia), sharing a partial orthographic core.
arXiv:2607. 18305v1 Announce Type: cross Abstract: Some limits on what language models know are not gaps in data coverage but structural properties of learning from text.
arXiv:2605. 23393v2 Announce Type: replace-cross Abstract: Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction.
arXiv:2606. 31845v1 Announce Type: cross Abstract: A transformer's feed-forward (FFN) sublayer materializes the distinctions attention gathers, yet gives no account of what it computes.
arXiv:2607. 18921v1 Announce Type: cross Abstract: Circuit extraction identifies a small set of model components whose presence preserves a target behavior under ablation, and the resulting circuit is often read as the mechanism behind that behavior.
arXiv:2607. 11696v1 Announce Type: new Abstract: Self-refinement often fails to strengthen few-shot inductive reasoning in large language models.