Related papers: Contrastive Sparse Autoencoders for Interpreting P…

Recent work has shown deep neural networks (DNNs) to be highly susceptible to well-designed, small perturbations at the input layer, or so-called adversarial examples. Taking images as an example, such distortions are often imperceptible,…

To advance the transparency of learning machines such as Deep Neural Networks (DNNs), the field of Explainable AI (XAI) was established to provide interpretations of DNNs' predictions. While different explanation techniques exist, a popular…

We introduce a new artificial intelligence (AI) approach called, the 'Digital Synaptic Neural Substrate' (DSNS). It uses selected attributes from objects in various domains (e.g. chess problems, classical music, renowned artworks) and…

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…

The increasing complexity and frequency of cyber-threats demand intrusion detection systems (IDS) that are not only accurate but also interpretable. This paper presented a novel IDS framework that integrated Explainable Artificial…

Variational autoencoders are powerful algorithms for identifying dominant latent structure in a single dataset. In many applications, however, we are interested in modeling latent structure and variation that are enriched in a target…

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multidimensional features.…

Deep neural networks (DNNs) have achieved impressive predictive performance due to their ability to learn complex, non-linear relationships between variables. However, the inability to effectively visualize these relationships has led to…

By composing graphical models with deep learning architectures, we learn generative models with the strengths of both frameworks. The structured variational autoencoder (SVAE) inherits structure and interpretability from graphical models,…

Artificial intelligence in healthcare requires models that are accurate and interpretable. We advance mechanistic interpretability in medical vision by applying Medical Sparse Autoencoders (MedSAEs) to the latent space of MedCLIP, a…

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

Sparse autoencoders (SAEs) emerged as a promising tool for mechanistic interpretability of transformer-based foundation models. Very recently, SAEs were also adopted for the visual domain, enabling the discovery of visual concepts and their…

Deep learning models for medical image classification usually achieve promising results but typically rely on large, annotated datasets or standard transfer learning from ImageNet. Self-Supervised Learning (SSL) has emerged as a powerful…

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

Explainable Artificial Intelligence (XAI) models have recently attracted a great deal of interest from a variety of application sectors. Despite significant developments in this area, there are still no standardized methods or approaches…

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…

Autonomous driving depends on perception systems to understand the environment and to inform downstream decision-making. While advanced perception systems utilizing black-box Deep Neural Networks (DNNs) demonstrate human-like comprehension,…

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…

Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable…

Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. The opacity of such black-box planners makes it challenging for the human behind the wheel to accurately anticipate when they will fail, with…