JK
Jan Kirchner
neurosciencecs.AIcs.CLcs.LGdevelopmentsynaptic plasticitydendritemouseadaptationAdaptation, Physiological
On Valency
published · living versionsW_5uruupn8·v1 · currentpublished
Auditing language models for hidden objectives
with Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey +30
1 version
Preprints & journals
18 papers in the corpus · 2017–2026Automated Researchers Can Mitigate Well-characterized Alignment Failures2608.28945v3 · Chen Yueh-Han, Jiaxin Wen, Jan Hendrik Kirchner2026 · 0 citationsarXiv
Humanity's Last Exam2501.14249v11 · Long Phan, Alice Gatti, Ziwen Han et al.2025 · 23 citationsarXiv
Correlated spontaneous activity sets up multi-sensory integration in the developing higher-order cortex10.1101/2024.07.19.603239v3 · Dwulet, J. M., Zabouri, N., Kirchner, J. H. et al.2024 · 3 citationsbioRxiv
Dendritic growth and synaptic organization from activity-independent cues and local activity-dependent plasticity.39899359 · Kirchner, Jan H, Euler, Lucas, Fritz, Ingo et al.2025 · 17 citationseLife. 2025;12
Auditing language models for hidden objectives2503.10965v2 · Samuel Marks, Johannes Treutlein, Trenton Bricken et al.2025 · 4 citationsarXivon Valency
Dendritic growth and synaptic organization from activity-independent cues and local activity-dependent plasticity10.1101/2022.05.24.493217v3 · Kirchner, J. H., Euler, L., Fritz, I. et al.2022 · 17 citationsbioRxiv
Prover-Verifier Games improve legibility of LLM outputs2407.13692v2 · Jan Hendrik Kirchner, Yining Chen, Harri Edwards et al.2024 · 2 citationsarXiv
Understanding polysemanticity in neural networks through coding theory2401.17975v1 · Simon C. Marshall, Jan H. Kirchner2024 · 0 citationsarXiv
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision2312.09390v1 · Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner et al.2023 · 25 citationsarXiv
Emergence of synaptic organization and computation in dendrites.35881644 · Kirchner, Jan H, Gjorgjieva, Julijana2023 · 22 citationsNeuroforum. 2022;28(1):21-30
Researching Alignment Research: Unsupervised Analysis2206.02841v1 · Jan H. Kirchner, Logan Smith, Jacques Thibodeau et al.2022 · 2 citationsarXiv
Oxytocin Shapes Spontaneous Activity Patterns in the Developing Visual Cortex by Activating Somatostatin Interneurons.33157028 · Maldonado, Paloma P, Nuno-Perez, Alvaro, Kirchner, Jan H et al.2021 · 50 citationsCurrent biology : CB. 2021;31(2):322-333.e5
Adaptation of spontaneous activity in the developing visual cortex.33722342 · Wosniack, Marina E, Kirchner, Jan H, Chao, Ling-Ya et al.2021 · 39 citationseLife. 2021;10
Emergence of local and global synaptic organization on cortical dendrites.34183661 · Kirchner, Jan H, Gjorgjieva, Julijana2021 · 71 citationsNature communications. 2021;12(1):4005
Adaptation of spontaneous activity in the developing visual cortex10.1101/2020.07.30.229559v1 · Wosniack, M. E., Kirchner, J. H., Chao, L.-Y. et al.2020 · 39 citationsbioRxiv
Oxytocin shapes spontaneous activity patterns in the developing visual cortex by activating somatostatin interneurons10.1101/866251v1 · Maldonado, P. P., Nuno-Perez, A., Kirchner, J. et al.2019 · 50 citationsbioRxiv
A unifying framework for synaptic organization on cortical dendrites10.1101/771907v1 · Kirchner, J. H., Gjorgjieva, J.2019 · 8 citationsbioRxiv
Large Deviation Theory for Parameter Estimation in Simple Neuron Models1707.04648v1 · Jan H. Kirchner2017 · 0 citationsarXiv
Career total: 33 works. 18 are in this corpus.
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.