| Topic | Keywords | Jupyter Notebook | Colab Link |
|---|---|---|---|
| Interpreting LLMs for text generation | Llama, Shapley values, Integrated gradients | LLM_Attribution_with_Llama |  |
| Interpreting BERT QA models | BERT, embeddings, attention attributions | BERT_QA_Interpretability | |
| Interpreting BERT QA models | BERT, attention matrices, importance scores | BERT_QA_Interpretability2 | |
| Logit Lens Example | Logit Lens | LogitLens | |
| Mini Project | |
| Mini Project (with solution) | |