Simon Willison’s Weblog

Decomposing Language Models Into Understandable Components. Anthropic appear to have made a major breakthrough with respect to the interpretability of Large Language Models:

“[...] we outline evidence that there are better units of analysis than individual neurons, and we have built machinery that lets us find these units in small transformer models. These units, called features, correspond to patterns (linear combinations) of neuron activations. This provides a path to breaking down complex neural networks into parts we can understand”