arXiv Machine Learning
SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 8
Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers
arXiv:2606. 06664v1 Announce Type: cross Abstract: Despite high accuracy, Vision Transformer (ViT) predictions can be driven by spurious cues, raising the need to understand their inner workings before safe deployment.
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 AI
Oct 9
The Polytopal Neural Network
The paper introduces Polytopal Neural Networks (PNNs), a framework that enforces a polytope-based structure on neural network representations to extract distinct layer-wise aspects. By using learned corpus representations and an amortized simplex inference procedure, PNNs preserve meaningful latent structures with minimal performance loss and yield compressed representations comparable to vector‑quantized (VQ) methods. The authors demonstrate that PNNs provide a new, interpretable approach to VQ deep learning training while maintaining competitive performance.
arXiv Machine Learning
Oct 9
Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study
The paper presents a detailed study of feature representations in Vision Transformers (ViTs), revealing that feature collapse at initialization causes redundancy and proposing a reduction scheme to address it. It demonstrates that entropy and minimum eigenvalue metrics reliably predict generalization, and that token‑space features and linear submodule outputs are particularly informative. The authors develop a proxy that improves ranking of ViT architectures by 18‑48% over previous baselines, enabling the selection of models with higher accuracy at comparable or lower computational cost.
arXiv Machine Learning
Jun 8
Sparsely gated tiny linear experts
arXiv:2606. 07414v1 Announce Type: new Abstract: Sparsity allows scaling model parameters without proportionally increasing computational cost.
arXiv Machine Learning
Jul 2
Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
arXiv:2607. 00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact.