event

GPT-2 Visualization Event

3 items · started 2026-10-27 · closed 2026-10-30

  1. Pruned language models are judged almost entirely by accuracy and perplexity, which assumes that preserved output behaviour implies preserved internal computation. We test this assumption with a factorial pruning study on GPT-2, crossing t…

  2. Knowledge distillation compresses large language models into compact students that preserve aggregate metrics, yet the mechanistic consequences of depth-reduction distillation remain largely uncharacterized. This work applies linear CKA, l…

  3. An interactive 3D walk through GPT-2. Type a sentence and watch every matrix operation, with the real numbers, computed in your browser.

← all threads