The rising popularity of explainable artificial intelligence (XAI) to understand high-performing
black boxes raised the question of how to evaluate explanations of machine learning (ML) …

Neural networks for NLP are becoming increasingly complex and widespread, and there is a
growing concern if these models are responsible to use. Explaining models helps to address …

Through considerable effort and intuition, several recent works have reverse-engineered
nontrivial behaviors oftransformer models. This paper systematizes the mechanistic …

Large language models (LLMs) have demonstrated impressive capabilities in natural
language processing. However, their internal mechanisms are still unclear and this lack of …

Abstract Concept Bottleneck Models (CBM) are inherently interpretable models that factor
model decisions into human-readable concepts. They allow people to easily understand …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Research in mechanistic interpretability seeks to explain behaviors of machine learning
models in terms of their internal components. However, most previous work either focuses …

Abstract Language models learn a great quantity of factual information during pretraining,
and recent work localizes this information to specific model weights like mid-layer MLP …

Feed-forward layers constitute two-thirds of a transformer model's parameters, yet their role
in the network remains under-explored. We show that feed-forward layers in transformer …

The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …