我想要一天分享一點「LLM從底層堆疊的技術」，並且每篇文章長度控制在三分鐘以內，讓大家不會壓力太大，但是又能夠每天成長一點。
以下附上參考項目：
- BertViz: https://github.com/jessevig/BertViz
- Zeyu Yun, Yubei Chen, Bruno A. Olshausen, Yann LeCun, 2021, Transformer visualization via dictio- nary learning: contextualized embedding as a linear superposition of transformer factors: https:// arxiv.org/abs/2103.15949
- Hugging Face with Slunberg SHAP: https://github.com/slundberg/SHAPTransformer
- Visualization via dictionary learning: https://transformervis.github.io/transformervis/
- OpenAI, Large Language Models can explain neurons in language models: https://openai.com/ research/language-models-can-explain-neurons-in-language-models
- OpenAI neuro explainer paper: https://openaipublic.blob.core.windows.net/neuron- explainer/paper/index.html
- LIT: https://pair-code.github.io/lit/
以下附上額外閱讀項目：
- Hoover et al., 2021, exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models: https://arxiv.org/abs/1910.05276
- Jesse Vig, 2019, A Multiscale Visualization of Attention in the Transformer Model: https:// aclanthology.org/P19-3007.pdf
