Zobrazeno 1 - 10
of 2 353
pro vyhledávání: '"Karvonen, P"'
Sparse Autoencoders (SAEs) are an interpretability technique aimed at decomposing neural network activations into interpretable units. However, a major bottleneck for SAE development has been the lack of high-quality performance metrics, with prior w
Externí odkaz:
http://arxiv.org/abs/2411.18895
The advantage of quantum protocols lies in the inherent properties of the shared quantum states. These states are sometimes provided by sources that are not trusted, and therefore need to be verified. Finding secure and efficient quantum state verifi
Externí odkaz:
http://arxiv.org/abs/2411.04767
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
Autor:
Karvonen, Adam, Wright, Benjamin, Rager, Can, Angell, Rico, Brinkmann, Jannik, Smith, Logan, Verdun, Claudio Mayrink, Bau, David, Marks, Samuel
What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the quality of
Externí odkaz:
http://arxiv.org/abs/2408.00113
We study numerical integration by combining the trapezoidal rule with a M\"obius transformation that maps the unit circle onto the real line. We prove that the resulting transformed trapezoidal rule attains the optimal rate of convergence if the inte
Externí odkaz:
http://arxiv.org/abs/2407.13650
Autor:
Karvonen, Toni, Zhigljavsky, Anatoly
We identify a large class of positive-semidefinite kernels for which a certain polynomial rate of convergence of maximum mean discrepancies of Farey sequences is equivalent to the Riemann hypothesis. This class includes all Mat\'ern kernels of order
Externí odkaz:
http://arxiv.org/abs/2407.10214
Autor:
Hofstra, Pieter, Karvonen, Martti
Publikováno v:
Theory and Applications of Categories, Vol. 42, No. 2, 2024, pp. 19-40
Abstract inner automorphisms can be used to promote any category into a 2-category, and we study two-dimensional limits and colimits in the resulting 2-categories. Existing connected colimits and limits in the starting category become two-dimensional
Externí odkaz:
http://arxiv.org/abs/2406.13647
The Helsinki Speech Challenge 2024 (HSC2024) invites researchers to enhance and deconvolve speech audio recordings. We recorded a dataset that challenges participants to apply speech enhancement and inverse problems techniques to recorded speech data
Externí odkaz:
http://arxiv.org/abs/2406.04123
Autor:
Karvonen, Adam
Language models have shown unprecedented capabilities, sparking debate over the source of their performance. Is it merely the outcome of learning syntactic patterns and surface level statistics, or do they extract semantics and a world model from the
Externí odkaz:
http://arxiv.org/abs/2403.15498
Autor:
Suzuki, Yuya, Karvonen, Toni
This paper studies function approximation in Gaussian Sobolev spaces over the real line and measures the error in a Gaussian-weighted $L^p$-norm. We construct two linear approximation algorithms using $n$ function evaluations that achieve the optimal
Externí odkaz:
http://arxiv.org/abs/2402.02917
What is a time-varying graph, or a time-varying topological space and more generally what does it mean for a mathematical structure to vary over time? Here we introduce categories of narratives: powerful tools for studying temporal graphs and other t
Externí odkaz:
http://arxiv.org/abs/2402.00206