Understanding AI systems' inner workings is critical for ensuring value alignment and safety.
This review explores mechanistic interpretability: reverse engineering the computational …

Deep neural networks (DNNs) are machine learning algorithms that have revolutionized
computer vision due to their remarkable successes in tasks like object classification and …

As AI technology is increasingly applied to high-impact, high-risk domains, there have been
a number of new methods aimed at making AI models more human interpretable. Despite …

Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer
vision, yet we understand very little about why they work and what they learn. While existing …

How do neural networks extract patterns from pixels? Feature visualizations attempt to
answer this important question by visualizing highly activating patterns through optimization …

Feature visualization has gained significant popularity as an explainability method,
particularly after the influential work by Olah et al. in 2017. Despite its success, its …

In light of the recent widespread adoption of AI systems, understanding the internal
information processing of neural networks has become increasingly critical. Most recently …

Neuroscientists apply a range of analysis tools to recorded neural activity in order to glean
insights into how neural circuits drive behavior in organisms. Despite the fact that these tools …

Understanding the intricacies of fine-grained population distribution, including both
predictability and uncertainty, is crucial for urban planning, social equity, and environmental …

Causality and eXplainable Artificial Intelligence (XAI) have developed as separate fields in
computer science, even though the underlying concepts of causation and explanation share …