56 citations · 79 across the 14 of their papers we have counts for
14 papers
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
Adam Karvonen, James Chua, Clément Dumas +8
Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpreting them. Recent work…
LLMs Process Lists With General Filter Heads
Arnab Sen Sharma, Giordano Rogers, Natalie Shapira +1
We investigate the mechanisms underlying a range of list-processing tasks in LLMs, and we find that LLMs have learned to encode a compact, causal representation of a general filter…
Language Models use Lookbacks to Track Beliefs
Nikhil Prakash, Natalie Shapira, Arnab Sen Sharma +5
How do language models (LMs) represent characters' beliefs, especially when those beliefs may differ from reality? This question lies at the heart of understanding the Theory of Mi…
Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
Hiba Ahsan, Arnab Sen Sharma, Silvio Amir +2
We know from prior work that LLMs encode social biases, and that this manifests in clinical tasks. In this work we adopt tools from mechanistic interpretability to unveil sociodemo…
The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
Aaron Mueller, Jannik Brinkmann, Millicent Li +10
Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc ev…
NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
Jaden Fiotto-Kaufman, Alexander R. Loftus, Eric Todd +17
We introduce NNsight and NDIF, technologies that work in tandem to enable scientific study of the representations and computations learned by very large neural networks. NNsight is…
Locating and Editing Factual Associations in Mamba
Arnab Sen Sharma, David Atkinson, David Bau
We investigate the mechanisms of factual recall in the Mamba state space model. Our work is inspired by previous findings in autoregressive transformer language models suggesting t…
Function Vectors in Large Language Models
Eric Todd, Millicent L. Li, Arnab Sen Sharma +3
We report the presence of a simple neural mechanism that represents an input-output function as a vector within autoregressive transformer language models (LMs). Using causal media…
Linearity of Relation Decoding in Transformer Language Models
Evan Hernandez, Arnab Sen Sharma, Tal Haklay +5
Much of the knowledge encoded in transformer language models (LMs) may be expressed in terms of relations: relations between words and their synonyms, entities and their attributes…
Augmenting Online Classes with an Attention Tracking Tool May Improve Student Engagement
Arnab Sen Sharma, Mohammad Ruhul Amin, Muztaba Fuad
Online remote learning has certain advantages, such as higher flexibility and greater inclusiveness. However, a caveat is the teachers' limited ability to monitor student interacti…
Mass-Editing Memory in a Transformer
Kevin Meng, Arnab Sen Sharma, Alex Andonian +2
Recent work has shown exciting promise in updating large language models with new memories, so as to replace obsolete information or add specialized knowledge. However, this line o…
HS-BAN: A Benchmark Dataset of Social Media Comments for Hate Speech Detection in Bangla
Nauros Romim, Mosahed Ahmed, Md Saiful Islam +3
In this paper, we present HS-BAN, a binary class hate speech (HS) dataset in Bangla language consisting of more than 50,000 labeled comments, including 40.17% hate and rest are non…
Presenting a Larger Up-to-date Movie Dataset and Investigating the Effects of Pre-released Attributes on Gross Revenue
Arnab Sen Sharma, Tirtha Roy, Sadique Ahmmod Rifat +1
Movie-making has become one of the most costly and risky endeavors in the entertainment industry. Continuous change in the preference of the audience makes it harder to predict wha…
Automatic Detection of Satire in Bangla Documents: A CNN Approach Based on Hybrid Feature Extraction Model
Arnab Sen Sharma, Maruf Ahmed Mridul, Md Saiful Islam
Widespread of satirical news in online communities is an ongoing trend. The nature of satires is so inherently ambiguous that sometimes it's too hard even for humans to understand…