The Birth of Knowledge: Emergent Features across Time, Space, and Scale in Large Language Models

Shashata Sawmya, Micah Adler, Nir Shavit

The Birth of Knowledge: Emergent Features across Time, Space, and Scale in Large Language Models: 1 upvotes on Hugging Face Daily Papers, #66 of 71 papers on 2025-05-27. Day-by-day upvote history.

This paper studies the emergence of interpretable categorical features within large language models (LLMs), analyzing their behavior across training checkpoints (time), transformer layers (space), and varying model sizes (scale). Using sparse autoencoders for mechanistic interpretability, we identify when and where specific semantic concepts emerge within neural activations. Results indicate clear temporal and scale-specific thresholds for feature emergence across multiple domains. Notably, spatial analysis reveals unexpected semantic reactivation, with early-layer features re-emerging at later layers, challenging standard assumptions about representational dynamics in transformer models.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.