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
- Trying out the new Gemini 2.5 model family - 17th June 2025
- The lethal trifecta for AI agents: private data, untrusted content, and external communication - 16th June 2025
- An Introduction to Google’s Approach to AI Agent Security - 15th June 2025