arXiv Machine Learning

The Residual Stream's Effective Depth

The paper introduces effective depth (Deff), a scalar diagnostic that treats a transformer’s layer‑wise residual stream as a discrete‑time process and measures how representation similarity decays with layer distance. Across sixteen decoder‑only language models, Deff reveals that most models exhibit a lower similarity decay than the closed‑form reference, indicating correlated residual updates rather than unused depth. The study also shows that this effect is robust to various controls and persists early in training, suggesting Deff is a global accumulated‑state diagnostic rather than a capability score.

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
arXiv AI
Oct 28

What the Primary Lund Plane Omits: A Model-Stitching Diagnosis of a Jet-Tagger Representation Gap

The study investigates why Lund‑plane and Particle Transformer (ParT) jet taggers can perform differently by using model stitching to isolate representation from computation. By linking frozen early layers of one network to frozen late layers of another, the authors show that a known deficit in the primary Lund representation is purely representational, not computational, and that this gap is invisible in AUC but appears in background rejection at low signal efficiency. Rebuilding the representation on the full Cambridge/Aachen declustering tree largely closes the gap, revealing that the primary branch carries most of the discriminative power while secondary splittings mainly make the representation learnable.

By Saurabh Rai, Sanmay Ganguly
arXiv AI
Sep 18

Beyond Depth Truncation: Controlled Evaluation of Depth Utilization in Recursive Language Models

The paper critiques the common practice of evaluating depth usage in depth‑recurrent language models by truncating depth during inference and measuring performance decline. It argues that this method conflates three distinct effects—fewer block applications, reduced computation, and an out‑of‑distribution readout—yet is usually interpreted as measuring only the second. To address this, the authors introduce the Depth Control Protocol (DCP), a suite of positive and negative controls that isolate each factor, along with a training intervention to confirm causality, specifically tailored for depth‑wise weight‑sharing architectures.

By Ha Van Dau, Thanh Tung Khuat, Nguyen Thanh Dung
arXiv AI
Aug 24

Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation

The study investigates whether open‑weight language models can introspect on their own internal computations. Using the Open‑Weight Masked Introspection (OWMI) framework, researchers intervened on various internal components of eight models and asked them to report whether changes had occurred. Across 78,000 measurements, none of the models reliably distinguished real interventions from sham ones, with AUROC values essentially at chance. Why It Matters: The findings suggest that current open‑weight models lack the ability to audit their own internal states, highlighting a limitation for oversight that relies on a model’s self‑reporting.

By Emilio Ferrara
arXiv Machine Learning
Oct 16

Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics

The paper introduces Lexical Reference Frames (LexFrame) as a method to interpret language model residual streams by treating each hidden state as having a native reference frame induced by subsequent layers. Unlike fixed lenses or point‑cloud approaches, LexFrame reads a state through the model’s remaining layers using a set number of attention rounds, achieving high coherence (0.97) and accurate state reconstruction (within 0.16 nats). The approach also provides faithful attribution, token‑level steering, and potential early‑exit savings, making every hidden state readable, attributable, and steerable.

By Jian Gu, Hongyu Zhang, Chunyang Chen, Aldeida Aleti