SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model Paper • 2502.02737 • Published 2 days ago • 62
Sparse Autoencoders Collection SAEs are tools for understanding the internal representations of neural networks. These can be loaded using https://github.com/EleutherAI/sae • 7 items • Updated 11 days ago
Sparse Autoencoders Collection SAEs are tools for understanding the internal representations of neural networks. These can be loaded using https://github.com/EleutherAI/sae • 7 items • Updated 11 days ago