← Back to all news
arXiv Machine Learning By Giyeong Oh, Sunghee Ahn, Youngjae Yu

Reader--Writer Coupling in Transformer MLPs

Read the original on arXiv Machine Learning →

The paper investigates the dual roles of hidden channels in transformer MLPs, treating each channel as a reader that decides when to respond and a writer that determines what to add back to the residual stream. By examining the joint Jacobian of the MLP’s update, the authors identify a signed pairing coordinate that reveals a small core of strongly coupled reader–writer pairs, often with opposing signs. This opposed core appears early in training and persists across models, influencing how channels contribute to later layers and affecting the model’s output distribution.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
3d ago

The Geometry of Learning: Read-Write Asymmetry Across Training

The paper investigates how pretraining and alignment stages of transformer training affect weight updates in different matrix groups. By examining the residual stream’s shared coordinate system, it finds that alignment updates to query and key matrices align with the principal input subspace, whereas updates to output matrices remain largely random relative to the prediction subspace. This pattern persists across objectives and training stages, indicating that the geometry of updates is determined by the training phase rather than the specific objective.

By Valeria Ruscio, Keiran Thompson
llmssafety
More like this →
arXiv Computation and Language
Sep 10

Through the Looking Glass: Directly Reading and Writing Transformers

The paper investigates how many transformer components influence a token prediction by measuring the absolute contribution of each unit and channel to the logit. It finds that thousands of components contribute to a single prediction, yet a small subset—often just dozens—carries the majority of the predictive mass. Across models ranging from 124 M to 7 B parameters, the proportion of the model involved in a prediction remains around one to three percent, independent of size, and the study demonstrates that specific components can be directly read and written to modify model behavior without additional training.

By Mark Oskin
llmsrag
More like this →
arXiv Computation and Language
Aug 25

The Communication Map of a Transformer

The paper introduces the Communication Map, a method that charts every potential communication channel in a transformer model using only its weights. It generalizes previous coupling metrics into a single coefficient covering all 18 connection classes, revealing that 70‑89% of head pairs are non‑randomly oriented and identifying strong or avoiding couplings. The authors demonstrate the map’s utility by recovering known induction circuits and uncovering a two‑dimensional stream subspace whose removal eliminates induction capabilities across several models.

By Richard Zhe Wang
llmssafety
More like this →