Anthropic found a hidden space where Claude puzzles over concepts

· MIT Technology Review AI ·

Anthropic introduced the Jacobian lens, an interpretability technique for observing Claude’s internal concept processing during tasks.

Categories: Research

Excerpt

The AI firm Anthropic has developed a technique that has given it the clearest glimpse yet at what’s really going on inside large language models as they answer questions or carry out tasks. What they found ranges from the mundane to the unnerving. Researchers at the company built a tool called the Jacobian lens (or…