2018
Search results
Jun 28, 2024 · LOS ANGELES, CA (IANS) – Neel Nanda, the stand-up Indian American comedian, who appeared on ‘ Jimmy Kimmel Live !’ and ‘Comedy Central’s Adam Devine’s House Party ’, has died at the age of 32.
5 days ago · Work performed as a part of Neel Nanda's MATS 6.0 (Summer 2024) training program. TLDR. This is an interim report on reverse-engineering Othello-GPT, an 8-layer transformer trained to take sequences of Othello moves and predict legal moves. We find evidence that Othello-GPT learns to compute the board state using many independent decision rules ...
Jun 10, 2024 · This library was created by Neel Nanda and is maintained by Joseph Bloom. The core features of TransformerLens were heavily inspired by the interface to Anthropic's excellent Garcon tool. Credit to Nelson Elhage and Chris Olah for building Garcon and showing the value of good infrastructure for enabling exploratory research! Creator's Note ...
Jun 17, 2024 · Jacob Dunefsky, Philippe Chlenski, Neel Nanda. View a PDF of the paper titled Transcoders Find Interpretable LLM Feature Circuits, by Jacob Dunefsky and Philippe Chlenski and Neel Nanda. A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities.
Jun 29, 2024 · Deeply understand transformers: I have been using Neel Nanda’s Transformer Mechanistic Interpretability and implementing transformers from scratch. The resources listed in the blog post have been quite helpful! AI Safety and Alignment: I feel this is going well as part of SPAR.
Jun 29, 2024 · We engage in fascinating discussions with pre-eminent figures in the AI field. Our flagship show covers current affairs in AI, cognitive science, neuroscience and philosophy of mind with in-depth analysis. Our approach is unrivalled in terms of scope and rigour – we believe in intellectual….
Jun 27, 2024 · Rushing and Nanda [2024] Cody Rushing and Neel Nanda. Explorations of self-repair in language models. arXiv preprint arXiv:2402.15390, 2024. Sajjad et al. [2023] Hassan Sajjad, Fahim Dalvi, Nadir Durrani, and Preslav Nakov. On the effect of dropping layers of pre-trained transformer models. Computer Speech & Language, 77:101429, 2023.
