1:14:41 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Induction heads & Function vectors UofU Data Science 39 views - 6 days ago
1:16:22 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | QK & OV circuits UofU Data Science 28 views - 6 days ago
1:16:50 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Arithmetic circuits & Course review UofU Data Science 39 views - 6 days ago
1:17:40 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Attribution patching UofU Data Science 82 views - 3 weeks ago
42:38 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Activation patching UofU Data Science 67 views - 3 weeks ago
1:18:54 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Direct logit attribution & Logit lens UofU Data Science 55 views - 3 weeks ago
44:02 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Model diffing with crosscoders UofU Data Science 97 views - 4 weeks ago
33:26 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Probing: Part 2 UofU Data Science 88 views - 4 weeks ago
1:20:31 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Course review & Probing UofU Data Science 155 views - 4 weeks ago
1:09:03 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Attribution graphs: Edge weights & pruning UofU Data Science 177 views - 4 weeks ago
1:17:29 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | CLT → Attribution graph UofU Data Science 129 views - 4 weeks ago
49:55 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Transcoders UofU Data Science 192 views - 4 weeks ago
1:15:28 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | SAE advances: Part 2 UofU Data Science 211 views - 4 weeks ago
1:19:12 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | SAE use cases & training advances UofU Data Science 214 views - 1 month ago
1:12:08 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Evaluating SAE feature descriptions UofU Data Science 113 views - 1 month ago
1:11:40 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Generating SAE feature descriptions UofU Data Science 125 views - 1 month ago
37:05 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Linear representation hypothesis UofU Data Science 214 views - 1 month ago
19:39 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Sparse autoencoders: Basics UofU Data Science 144 views - 1 month ago
1:09:45 UUtah CS 6966 Interpretability of LLMs | Spring 2026 | Superposition UofU Data Science 500 views - 1 month ago
1:19:56 Lecture 27: Practical advice for using machine learning UofU Data Science 147 views - 11 months ago