deepseek-ai/DeepSeek-V4.1-Flash-1017 Image-Text-to-Text • 763B • Updated 5 days ago • 42.1k • • 2.22k
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining Paper • 2610.21025 • Published 8 days ago • 10
Sparse Readout Prism Collection Factorizing a model's final unembedding into a sparse feature basis for logit-lens analysis. • 2 items • Updated 6 days ago
Learning to Read Out (NeurIPS 2026) Collection Paper, readout dictionaries, controlled pretraining runs, W_U snapshots and an interactive feature atlas. • 5 items • Updated 6 days ago
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining Paper • 2610.21025 • Published 8 days ago • 10
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining Paper • 2610.21025 • Published 8 days ago • 10