Sign up to save your podcasts
Or
Share Episode 12.21: Interpretability, sparseness, and vector manipulation. Mono- and polysemanticity.
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Episode 12.21: Interpretability, sparseness, and vector manipulation. Mono- and polysemanticity.
More ‘caveat emptor’ than usual in this speculative episode based on three very important papers from Anthropic AI on interpretability, aka making sense of neural nets.
View all episodes
By John PuddefootMore ‘caveat emptor’ than usual in this speculative episode based on three very important papers from Anthropic AI on interpretability, aka making sense of neural nets.