SAEs in Formal Languages
Dr. David Krueger (University of Cambridge)
Posts by Collection
portfolio
Barvinok’s Algorithm
Dr. Tobias Grosser (University of Edinburgh)
Mutable Grammars
Dr. Tobias Grosser (University of Edinburgh)
Neural Factual Inconsistency Classification
Dr. Manish Gupta (IIIT-H, Microsoft)
publications
Neural models for Factual Inconsistency Classification with Explanations
Published in ECML PKDD, 2023
We categorize and present a dataset of factual inconsistencies, along with neural baselines for the classification of these inconsistencies.
Authors: Tathagata Raha, Mukund Choudhary, Abhinav Menon, Harshit Gupta, KV Aditya Srivatsa, Manish Gupta, Vasudeva Varma
Download Paper
Analyzing (In)Abilities of SAEs via Formal Languages
Published in MINT@NeurIPS, 2024
We formulate a synthetic testbed to stress-test the sparse autoencoder (SAE) approach to interpretability in the text domain, using formal languages.
Authors: Abhinav Menon, Manish Shrivastava, Ekdeep Singh Lubana, David Krueger
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching Assistant
Discrete Structures (undergraduate course), International Institute of Information Technology, 2022
I worked as a Teaching Assistant for the Discrete Structures course, which was meant to provide freshers with a grounding in basic abstract algebra and logic. This entailed setting and evaluating homework assignments and conducting refresher classes and clarification sessions.
Head Teaching Assistant
Introduction to NLP (undergraduate course), International Institute of Information Technology, 2023
I worked as a Head Teaching Assistant for the Introduction to NLP course, which was an introduction to the theory and implementation of NLP models (both classical and neural). I coordinated a team of six TAs, who worked to evaluate homework assignments, examinations and projects; conduct vivas; and teach the mathematical foundation of the broad concepts covered in the classroom.