Hypertrix: An indicatrix for high-dimensional visualizations

Authors: Raval, Shivam, Viegas, Fernanda, Wattenberg, Martin

Source: 2024 IEEE Visualization and Visual Analytics (VIS) VIS Visualization and Visual Analytics (VIS), 2024 IEEE. :1-5 Oct, 2024

Relation: 2024 IEEE Visualization and Visual Analytics (VIS)

Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models

Authors: Fel, Thomas, Lubana, Ekdeep Singh, Prince, Jacob S., Kowal, Matthew, Boutin, Victor, Papadimitriou, Isabel, Wang, Binxu, Wattenberg, Martin, Ba, Demba, Konkle, Talia

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2502.12892

Open Problems in Mechanistic Interpretability

Authors: Sharkey, Lee, Chughtai, Bilal, Batson, Joshua, Lindsey, Jack, Wu, Jeff, Bushnaq, Lucius, Goldowsky-Dill, Nicholas, Heimersheim, Stefan, Ortega, Alejandro, Bloom, Joseph, Biderman, Stella, Garriga-Alonso, Adria, Conmy, Arthur, Nanda, Neel, Rumbelow, Jessica, Wattenberg, Martin, Schoots, Nandi, Miller, Joseph, Michaud, Eric J., Casper, Stephen, Tegmark, Max, Saunders, William, Bau, David, Todd, Eric, Geiger, Atticus, Geva, Mor, Hoogland, Jesse, Murfet, Daniel, McGrath, Tom

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2501.16496

New 400 V SiC MOSFET and its use in Multi-Level Applications

Authors: Siemieniec, Ralf, Wattenberg, Martin, Kasper, Matthias, Bhandari, Jyotshna, Chen, Wei-Ju, Shim, Heejae, Pignatelli, Alberto, Jagannath, Sriram

Source: 2024 Energy Conversion Congress & Expo Europe (ECCE Europe) Energy Conversion Congress & Expo Europe (ECCE Europe), 2024. :1-7 Sep, 2024

Relation: 2024 Energy Conversion Congress & Expo Europe (ECCE Europe)

ICLR: In-Context Learning of Representations

Authors: Park, Core Francisco, Lee, Andrew, Lubana, Ekdeep Singh, Yang, Yongyi, Okawa, Maya, Nishi, Kento, Wattenberg, Martin, Tanaka, Hidenori

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2501.00070

Relational Composition in Neural Networks: A Survey and Call to Action

Authors: Wattenberg, Martin, Viégas, Fernanda B.

Subject Terms: Computer Science - Artificial Intelligence, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2407.14662

Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner

Authors: Li, Kenneth, Wang, Yiming, Viégas, Fernanda, Wattenberg, Martin

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2406.11978

Designing a Dashboard for Transparency and Control of Conversational AI

Authors: Chen, Yida, Wu, Aoyu, DePodesta, Trevor, Yeh, Catherine, Li, Kenneth, Marin, Nicholas Castillo, Patel, Oam, Riecke, Jan, Raval, Shivam, Seow, Olivia, Wattenberg, Martin, Viégas, Fernanda

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Human-Computer Interaction

Access URL: http://arxiv.org/abs/2406.07882

Q-Probe: A Lightweight Approach to Reward Maximization for Language Models

Authors: Li, Kenneth, Jelassi, Samy, Zhang, Hugh, Kakade, Sham, Wattenberg, Martin, Brandfonbrener, David

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2402.14688

Measuring and Controlling Instruction (In)Stability in Language Model Dialogs

Authors: Li, Kenneth, Liu, Tianle, Bashkansky, Naomi, Bau, David, Viégas, Fernanda, Pfister, Hanspeter, Wattenberg, Martin

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2402.10962

A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity

Authors: Lee, Andrew, Bai, Xiaoyan, Pres, Itamar, Wattenberg, Martin, Kummerfeld, Jonathan K., Mihalcea, Rada

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2401.01967

A Multi-Kilowatt Low-Profile GaN Inverter for Light Electric Vehicles and High-Power Tools

Authors: Wattenberg, Martin, Lorenz, Oscar G., Sanchez, Juan

Source: 2023 IEEE Applied Power Electronics Conference and Exposition (APEC) Applied Power Electronics Conference and Exposition (APEC), 2023 IEEE. :1443-1450 Mar, 2023

Relation: 2023 IEEE Applied Power Electronics Conference and Exposition (APEC)

Interactive AI Alignment: Specification, Process, and Evaluation Alignment

Authors: Terry, Michael, Kulkarni, Chinmay, Wattenberg, Martin, Dixon, Lucas, Morris, Meredith Ringel

Subject Terms: Computer Science - Human-Computer Interaction, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2311.00710

Efficiently Paralleling GaN-Transistors for High Current and High Frequency Applications Using a Butterfly Layout

Authors: Wattenberg, Martin, Lorenz, Oscar, Sanchez, Juan

Source: 2022 24th European Conference on Power Electronics and Applications (EPE'22 ECCE Europe) Power Electronics and Applications (EPE'22 ECCE Europe), 2022 24th European Conference on. :1-10 Sep, 2022

Relation: 2022 24th European Conference on Power Electronics and Applications (EPE’22 ECCE Europe)

ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing

Authors: Arawjo, Ian, Swoopes, Chelse, Vaithilingam, Priyan, Wattenberg, Martin, Glassman, Elena

Subject Terms: Computer Science - Human-Computer Interaction, Computer Science - Artificial Intelligence, H.5.2, I.2

Access URL: http://arxiv.org/abs/2309.09128

Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Authors: Nanda, Neel, Lee, Andrew, Wattenberg, Martin

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2309.00941

Linearity of Relation Decoding in Transformer Language Models

Authors: Hernandez, Evan, Sharma, Arnab Sen, Haklay, Tal, Meng, Kevin, Wattenberg, Martin, Andreas, Jacob, Belinkov, Yonatan, Bau, David

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2308.09124

Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model

Authors: Chen, Yida, Viégas, Fernanda, Wattenberg, Martin

Subject Terms: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2306.05720

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Authors: Li, Kenneth, Patel, Oam, Viégas, Fernanda, Pfister, Hanspeter, Wattenberg, Martin

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2306.03341

AttentionViz: A Global View of Transformer Attention

Authors: Yeh, Catherine, Chen, Yida, Wu, Aoyu, Chen, Cynthia, Viégas, Fernanda, Wattenberg, Martin

Subject Terms: Computer Science - Human-Computer Interaction, Computer Science - Computation and Language, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2305.03210