16 papers
Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models
Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik
Sparse autoencoders (SAEs) decompose language model activations into sparse features, but standard SAEs encode each token independently and do not expose information that persists…
Actionable Interpretability Must Be Defined in Terms of Symmetries
Pietro Barbiero, Mateo Espinosa Zarlenga, Francesco Giannini +4
This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpr…
The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics
Pietro Barbiero, Giovanni De Felice, Mateo Espinosa Zarlenga +5
As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their computations. However, i…
In Defense of Information Leakage in Concept-based Models
Mateo Espinosa Zarlenga
Concept-based models (CMs), deep neural networks that ground their predictions on representations aligned with human-understandable concepts (e.g., "round", "stripes", etc.), have…
Mixture of Concept Bottleneck Experts
Francesco De Santis, Gabriele Ciravegna, Giovanni De Felice +7
Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically constrain their task predictor…
CB-SLICE: Concept-Based Interpretable Error Slice Discovery
Yael Konforti, Mateo Espinosa Zarlenga, Elaf Almahmoud +1
Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Identifying these groups and the…