Contributed Talk Sessions | Poster Sessions | All Posters | Search Papers

Poster Session A: Tuesday, August 12, 1:30 – 4:30 pm, de Brug & E‑Hall

Transformer Dynamics: A Neuroscientific Approach to Interpretability of Large Language Models

Jesseba Fernando¹, Grigori Guitchounts²; ¹Northeastern University, ²Flagship Pioneering

Presenter: Jesseba Fernando

As artificial intelligence models have exploded in scale and capability, understanding of their internal mechanisms remains a critical challenge. Inspired by the success of dynamical systems approaches in neuroscience, here we propose a novel framework for studying computations in deep learning systems. We focus on the residual stream (RS) in transformer models, conceptualizing it as a dynamical system evolving across layers. We find that activations of individual RS units exhibit strong continuity across layers, despite the RS being a non-privileged basis. Activations in the RS accelerate and grow denser over layers. In reduced-dimensional spaces, the RS follows a curved trajectory with attractor-like dynamics in the lower layers. These insights bridge dynamical systems theory and mechanistic interpretability, establishing a foundation for a “neuroscience of AI” that combines theoretical rigor with large-scale data analysis to advance our understanding of modern neural networks.

Topic Area: Language & Communication

Extended Abstract: Full Text PDF