TLDR Tech / AI
No Space Like J-Space
The 'J-space' is the area of conscious access where things are available for a model to do what humans could call conscious reasoning. It is named after an interpretability technique called the Jacobian Lens, which computes, for each layer, the average causal effect of changes in the residual stream of a model's eventual outputs, averaged across a wide variety of contexts. This allows researchers to trace what concepts are associated with each layer as the model proceeds through. The J-space and J-lens are remarkably effective tools and mark a major advance in our understanding of LLMs.
Read the full story