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 Skills are awesome, maybe a bigger deal than MCP - 16th October 2025
- NVIDIA DGX Spark: great hardware, early days for the ecosystem - 14th October 2025
- Claude can write complete Datasette plugins now - 8th October 2025