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
- My review of Claude's new Code Interpreter, released under a very confusing name - 9th September 2025
- Recreating the Apollo AI adoption rate chart with GPT-5, Python and Pyodide - 9th September 2025
- GPT-5 Thinking in ChatGPT (aka Research Goblin) is shockingly good at search - 6th September 2025