A Deeper Analysis of Block-Sparse Featurizers
This work proposes several architectural changes to the BSF, including a Tournament Top-K selection rule that significantly reduces feature splitting, and extends the block paradigm to the crosscoder.
2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work proposes several architectural changes to the BSF, including a Tournament Top-K selection rule that significantly reduces feature splitting, and extends the block paradigm to the crosscoder.
This work plants a controllable latent variable inside natural-looking text and arranges the 8 states themselves on a ring, in the exact order of the Markov chain, which is supporting evidence that a concept's geometry can be formed by the statistical dynamics of the latent variable behind it.