JL
neurosciencecs.LGcs.CLcs.AIcs.NECorpus Striatummemorynoneq-bio.NCNeurons

On Valency

published · living versions
W_5uruupn8·v1 · currentpublished
Auditing language models for hidden objectives
with Samuel Marks, Johannes Treutlein, Trenton Bricken, Jonathan Marcus +30
1 version

Preprints & journals

37 papers in the corpus · 2017–2026
Humanity's Last Exam2501.14249v11 · Long Phan, Alice Gatti, Ziwen Han et al.2025 · 23 citationsarXiv
Barcode activity in a recurrent network model of the hippocampus enables efficient memory binding.41504599 · Fang, Ching, Lindsey, Jack W, Abbott, Larry F et al.2026 · 1 citationeLife. 2026;14
Slot Machines: How LLMs Keep Track of Multiple Entities2604.21139v1 · Paul C. Bogdan, Jack Lindsey2026 · 0 citationsarXiv
Emotion Concepts and their Function in a Large Language Model2604.07729v1 · Nicholas Sofroniew, Isaac Kauvar, William Saunders et al.2026 · 4 citationsarXiv
Striatum-wide dopamine encodes trajectory errors separated from value.41673148 · Brown, Eleanor H, Zi, Yihan, Vu, Mai-Anh et al.2026 · 3 citationsNature. 2026;652(8109):424-433
The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models2601.10387v1 · Christina Lu, Jack Gallagher, Jonathan Michala et al.2026 · 4 citationsarXiv
Dynamics of striatal action selection and reinforcement learning.40338017 · Lindsey, Jack W, Markowitz, Jeffrey, Gillis, Winthrop F et al.2025 · 6 citationseLife. 2025;13
Auditing language models for hidden objectives2503.10965v2 · Samuel Marks, Johannes Treutlein, Trenton Bricken et al.2025 · 4 citationsarXivon Valency
Open Problems in Mechanistic Interpretability2501.16496v1 · Lee Sharkey, Bilal Chughtai, Joshua Batson et al.2025 · 11 citationsarXiv
Dynamics of striatal action selection and reinforcement learning10.1101/2024.02.14.580408v3 · Lindsey, J., Markowitz, J. E., Gillis, W. F. et al.2024 · 12 citationsbioRxiv
The role of motor cortex in motor sequence execution depends on demands for flexibility.39496797 · Mizes, Kevin G C, Lindsey, Jack, Escola, G Sean et al.2024 · 34 citationsNature neuroscience. 2024;27(12):2466-2475
Spatially organized striatal neuromodulator release encodes trajectory errors10.1101/2024.08.13.607797v1 · Brown, E. H., Zi, Y., Vu, M.-A. T. et al.2024 · 0 citationsbioRxiv
Selective consolidation of learning and memory via recall-gated plasticity.39023518 · Lindsey, Jack W, Litwin-Kumar, Ashok2024 · 5 citationseLife. 2024;12
Factorized visual representations in the primate visual system and deep neural networks.38968311 · Lindsey, Jack W, Issa, Elias B2024 · 11 citationseLife. 2024;13
Task structure and nonlinearity jointly determine learned representational geometry2401.13558v1 · Matteo Alleman, Jack W Lindsey, Stefano Fusi2024 · 7 citationsarXiv
Dissociating the contributions of sensorimotor striatum to automatic and visually guided motor sequences.37667040 · Mizes, Kevin G C, Lindsey, Jack, Escola, G Sean et al.2023 · 62 citationsNature neuroscience. 2023;26(10):1791-1804
Motor cortex is required for flexible but not automatic motor sequences10.1101/2023.09.05.556348v1 · Mizes, K. G. C., Lindsey, J., Escola, G. S. et al.2023 · 9 citationsbioRxiv
Sequence Learning and Consolidation on Loihi using On-chip Plasticity2205.00643v1 · Jack Lindsey, James B Aimone2022 · 3 citationsarXiv
Modularity and robustness of frontal cortical networks.34214471 · Chen, Guang, Kang, Byungwoo, Lindsey, Jack et al.2022 · 81 citationsCell. 2021;184(14):3717-3730.e24
The connectome of the adult Drosophila mushroom body provides insights into function.33315010 · Li, Feng, Lindsey, Jack W, Marin, Elizabeth C et al.2021 · 445 citationseLife. 2020;9
Learning to Learn with Feedback and Local Plasticity2006.09549v1 · Jack Lindsey, Ashok Litwin-Kumar2020 · 7 citationsarXiv
A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNs1901.00945v1 · Jack Lindsey, Samuel A. Ocko, Surya Ganguli et al.2019 · 90 citationsInternational Conference on Learning Representations, 2019 https://openreview.net/forum?id=S1xq3oR5tQ
The emergence of multiple retinal cell types through efficient coding of natural movies10.1101/458737v1 · Ocko, S. A., Lindsey, J., Ganguli, S. et al.2018 · 47 citationsbioRxiv
Pre-training Attention Mechanisms1712.05652v1 · Jack Lindsey2017 · 1 citationarXiv
Career total: 71 works. 37 are in this corpus.Showing the 33 most recent.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.