arXiv:2606. 00230v1 Announce Type: new Abstract: Grokking, the phenomenon in which neural networks generalize long after fitting their training data, has been studied in supervised settings on many epochs.
The paper investigates whether linguistic and arithmetic tasks in large language models (LLMs) rely on shared neural circuits. Using mechanistic interpretability techniques on five LLMs, the authors find that circuit similarity aligns primarily with task domain rather than input/output vocabularies or syntactic structure. This suggests that LLMs may employ largely separate neural circuits for language and arithmetic, indicating a modular organization of abilities.
arXiv:2605.24585v3 Announce Type: replace Abstract: Neural language models are typically trained on next-token prediction, although linguistic structure spans multiple temporal scales. Successor repr...
arXiv:2610.19041v1 Announce Type: new Abstract: Understanding the dynamics of language acquisition in Large Language Models (LLMs) is crucial for uncovering how statistical representations evolve int...
arXiv:2607.20995v2 Announce Type: replace Abstract: Distinguishing animate from inanimate concepts in written language requires more than shallow text processing, as it involves recognizing complex s...
The paper investigates when a language model actually learns task information versus when its readout (unembedding matrix) learns to express that information. Using a new parameter‑trajectory cross‑coding method, the authors find that hidden states can encode task data early in training, but the readout reorganizes only in a narrow window (0.4–1.1% of Pythia’s pretraining). By varying the readout learning rate, they show that faster readout learning reduces the gap between hidden‑state encoding and output expression without affecting final performance.
arXiv:2609.24821v1 Announce Type: new Abstract: The Linear Representation Hypothesis associates high-level concepts with directions in language models, but it remains unclear how these concept-relate...
The paper investigates natural language autoencoders (NLAs) as tools for verbalizing activation differences in large language models. It examines whether NLAs capture compositional structure, generalize to fine‑tuned models, recover fine‑tuning objectives, and can be specialized for model diffing. Experiments across four models show that NLAs largely succeed in these tasks, though they do not yet match state‑of‑the‑art diffing methods on emergent misalignment detection.
The paper investigates whether attention heads in transformer language models that specialize in syntactic relations causally influence the models’ syntactic predictions. Experiments show mixed to negative evidence: even when these heads are forced to attend to a distractor noun, the model’s predictions still favor the correct subject. Interventions on syntax-specialized heads affect predictions more than random heads, but only for one of two proposed measures.
The paper investigates natural language autoencoders (NLAs) that convert large language model activations into readable text. It examines whether NLAs capture compositional structure, generalize to fine‑tuned models, recover fine‑tuning objectives, and can be specialized for model diffing. Experiments across multiple models show positive results: NLAs preserve compositionality, transfer to lightweight fine‑tunes, recover hidden objectives, and outperform a black‑box baseline on diffing tasks, though they lag behind state‑of‑the‑art methods for misalignment detection.
The Linear Representation Hypothesis associates high-level concepts with directions in language models, but it remains unclear how these concept-related linear structures are organized within the mode...
arXiv:2608. 14681v1 Announce Type: cross Abstract: Words recur constantly in natural language use, yet it remains unclear whether language models reactivate prior representations or re-evaluate repeated words afresh, and whether post-training changes this default behavior.