Boolean elements in the Bruhat order Y Gao, K Hänni arXiv preprint arXiv:2007.08490, 2020 | 6 | 2020 |
Using Degeneracy in the Loss Landscape for Mechanistic Interpretability L Bushnaq, J Mendel, S Heimersheim, D Braun, N Goldowsky-Dill, ... arXiv preprint arXiv:2405.10927, 2024 | 5 | 2024 |
Mathematical models of computation in superposition K Hänni*, J Mendel*, D Vaintrob*, L Chan arXiv preprint arXiv:2408.05451, 2024 | 3 | 2024 |
The local interaction basis: Identifying computationally-relevant and sparsely interacting features in neural networks L Bushnaq, S Heimersheim, N Goldowsky-Dill, D Braun, J Mendel, ... arXiv preprint arXiv:2405.10928, 2024 | 2 | 2024 |
Toward A Mathematical Framework for Computation in Superposition D Vaintrob*, J Mendel*, K Hänni* AI Alignment Forum, 2024 | 2* | 2024 |
Wilf equivalence in Weyl groups and signed permutations K Hänni | 2 | 2019 |
Asymptotics of descent functions K Hänni arXiv preprint arXiv:2011.14360, 2020 | 1 | 2020 |
The probability of selecting edge-disjoint Hamilton cycles in the complete graph A Ferber, K Haenni, V Jain arXiv preprint arXiv:2001.01149, 2020 | 1 | 2020 |
Cluster-Norm for Unsupervised Probing of Knowledge W Laurito, S Maiya, G Dhimoïla, K Hänni arXiv preprint arXiv:2407.18712, 2024 | | 2024 |
Moral Experiments (draft) R Popper, K Hänni | | 2023 |
Constraints on rational decision-making under moral uncertainty (draft) K Hänni, R Popper | | 2023 |
Counting signed vexillary permutations Y Gao, K Hänni Advances in Applied Mathematics 121, 102106, 2020 | | 2020 |