Explaining GPT-2-Small Forward Passes with Edge-Level Autoencoder Circuits
"模型解释性" 相关文章
Simply reverse engineering gpt2-small (Layer 0, Part 1: Attention)
Black-box interpretability methodology blueprint: Probing runaway optimisation in LLMs
Can We Really Trust AI’s Chain-of-Thought Reasoning?
Some OthelloGPT Circuits
Enumerating objects a model "knows" using entity-detection features.
Learning Multi-Level Features with Matryoshka SAEs
The ‘strong’ feature hypothesis could be wrong
通过AI寻找科学真理，距离我们还有多远？对话深度原理创始人、新神经网络架构KAN作者｜DeepTalk播客更新
Interpreting Preference Models w/ Sparse Autoencoders
