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

Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to
understand a neural network model by reverse-engineering its internal computations …

Transformer large language models (LLMs) have sparked admiration for their exceptional
performance on tasks that demand intricate multi-step reasoning. Yet, these models …

Mechanistic interpretability seeks to understand the internal mechanisms of machine
learning models, where localization--identifying the important model components--is a key …

We study whether transformers can learn to implicitly reason over parametric knowledge, a
skill that even the most capable language models struggle with. Focusing on two …

The rapid progress of research aimed at interpreting the inner workings of advanced
language models has highlighted a need for contextualizing the insights gained from years …

Neural networks trained by gradient descent (GD) have exhibited a number of surprising
generalization behaviors. First, they can achieve a perfect fit to noisy training data and still …

Recent work by Power et al.(2022) highlighted a surprising" grokking" phenomenon in
learning arithmetic tasks: a neural net first" memorizes" the training set, resulting in perfect …

Prior work has found that pretrained language models (LMs) fine-tuned with different
random seeds can achieve similar in-domain performance but generalize differently on tests …

We study the recently discovered “grokking” phenomenon in deep learning [Power et al.,
2022], where neural networks generalize to unseen data abruptly, long after memorizing …