Pretrained benchmark transformers described in this blog post: https://www.lesswrong.com/posts/jeoSoJQLuK4JWqtyy/crafting-polysemantic-transformer-benchmarks-with-known
Pretrained benchmark transformers described in this blog post: https://www.lesswrong.com/posts/jeoSoJQLuK4JWqtyy/crafting-polysemantic-transformer-benchmarks-with-known