8th October 2023 - Link Blog
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”
Recent articles
- Locating the source of a mysterious beep with Claude - 9th November 2026
- Hide your slop PR descriptions behind <details><summary> - 9th November 2026
- Qwen 3.8 27B on my laptop can interpret model weights, too - 3rd November 2026
- The U.S. Census Bureau and “Super Intelligence” - 2nd November 2026