Hugging Face Trending Papers
Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computation and Language
Aug 25
Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation
arXiv:2608.22034v1 Announce Type: new Abstract: Mechanistic interpretability has identified transformer circuits, but lacks a shared vocabulary for describing how their functions compose across tasks...
arXiv AI
Sep 1
Concepts Whisper: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations
arXiv:2605.01609v2 Announce Type: replace-cross Abstract: We find that transformer concept representations systematically anti-concentrate in the spectral tail of the unembedding covariance, encoding...
arXiv Machine Learning
Aug 14
Geometric and Behavioral Stratification in Transformer Residual Streams
arXiv:2608. 12447v1 Announce Type: new Abstract: Trained transformer models develop privileged bases: coordinate axes whose statistics differ from the rest of the residual stream.
arXiv Machine Learning
Sep 22
Disassociating performance from compositional feature learning
arXiv:2505.09716v4 Announce Type: replace Abstract: Out-of-distribution (OOD) generalisation through composition requires a system to discover invariant properties from input-output associations and...
arXiv Machine Learning
Jul 9
Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning
arXiv:2607. 07316v1 Announce Type: new Abstract: This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms of modern neural networks.
arXiv Machine Learning
Jun 29
Prism Transformer: Progressive Head Schedules for Hierarchical Attention Processing
arXiv:2606. 27449v1 Announce Type: new Abstract: Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational subspace dimension (dh = dmodel/h) throughout the models depth.