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
- AI assisted search-based research actually works now - 21st April 2025
- Maybe Meta's Llama claims to be open source because of the EU AI act - 19th April 2025
- Image segmentation using Gemini 2.5 - 18th April 2025