InDeep PhD candidate Hosein Mohebbi organizes monthly online Zoom meetings with talks and discussion on recent research on interpretability. The Journal Club is especially meant for PhD students connected to the InDeep project, but everybody interested is welcome. Reach out to h.mohebbi@tilburguniversity.edu if you would like to join the talks.
Date | Speaker | Topic/Paper |
Jun 2024 | Martijn Bentum | TBA |
May 2024 | Marcel Vélez | Exploring the Inner Mechanisms of Large Generative Music Models |
Apr 2024 | Jonathan Kamp | The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement |
Feb 2024 | Verna Dankers, University of Edinburgh | Memorisation in translation and classification: the what and the where |
Nov 2023 | Ariana Bisazza | Can modern LMs be truly polyglot? |
Oct 2023 | Charlotte Pouw | Explaining Phone-Grapheme Mapping in Neural ASR models: A Case-Study on Place Assimilation |
Sep 2023 | Jane Arleth dela Cruz | NoNE Found: Explaining the Output of Sequence-to-Sequence Models when No Named Entity is Recognized |
May 2023 | John Ashley Burgoyne | Music Representation Learning |
Apr 2023 | Tom Lentz | Discovering Structure in Speech |
Mar 2023 | Oskar van der Wal, University of Amsterdam | The Birth of Bias: A case study on the evolution of gender bias in an English language model |
Mar 2023 | reading group led by Hosein Mohebbi | Data distributional properties drive emergent in-context learning in transformers |
Feb 2023 | reading group led by Michael Hanna | Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small |
Nov 2022 | Sara Rajaee, University of Amsterdam | The Isotropy of Contextualized Spaces |
Nov 2022 | reading group led by Jaap Jumelet | Toy Models of Superposition |
Apr 2022 | reading group led by Grzegorz Chrupała | Layer-wise Analysis of a Self-supervised Speech Representation Model |
Feb 2022 | reading group led by Hosein Mohebbi | Evaluating Explanations: How much do explanations from the teacher aid students? |
Feb 2022 | reading group led by Jonathan Kamp | Interpretable Reinforcement Learning |
Feb 2022 | reading group led by Gabriele Sarti | A Mathematical Framework for Transformer Circuits |
Jan 2022 | reading group led by Hosein Mohebbi | Incorporating Residual and Normalization Layers into Analysis of Masked Language Models |