苦研10年无果，千万经费打水漂，AI黑箱依然无解，谷歌撕破脸
"稀疏自编码器" 相关文章
苦研10年无果，千万经费打水漂！AI黑箱依然无解，谷歌撕破脸
苦研10年无果，千万经费打水漂！AI黑箱依然无解，谷歌撕破脸
Interpretable Fine Tuning Research Update and Working Prototype
Negative Results on Group SAEs
This AI Paper Introduces a Short KL+MSE Fine-Tuning Strategy: A Low-Cost Alternative to End-to-End Sparse Autoencoder Training for Interpretability
Takeaways From Our Recent Work on SAE Probing
Enhancing Instruction Tuning in LLMs: A Diversity-Aware Data Selection Strategy Using Sparse Autoencoders
Topological Data Analysis and Mechanistic Interpretability
比知识蒸馏好用，田渊栋等提出连续概念混合，再度革新Transformer预训练框架
Sparse Autoencoder Feature Ablation for Unlearning
Cross-Layer Feature Alignment and Steering in Large Language Model
MATS Applications + Research Directions I'm Currently Excited About
Empirical Insights into Feature Geometry in Sparse Autoencoders
Easily Evaluate SAE-Steered Models with EleutherAI Evaluation Harness
Good Fire AI Open-Sources Sparse Autoencoders (SAEs) for Llama 3.1 8B and Llama 3.3 70B
Scaling Sparse Feature Circuit Finding to Gemma 9B
What are polysemantic neurons?
Learning Multi-Level Features with Matryoshka SAEs
Matryoshka Sparse Autoencoders
