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
- Claude Code for web - a new asynchronous coding agent from Anthropic - 20th October 2025
- Getting DeepSeek-OCR working on an NVIDIA Spark via brute force using Claude Code - 20th October 2025
- Claude Skills are awesome, maybe a bigger deal than MCP - 16th October 2025