Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Engels, Joshua"'
Sparse autoencoders (SAEs) are a promising technique for decomposing language model activations into interpretable linear features. However, current SAEs fall short of completely explaining model performance, resulting in "dark matter": unexplained v
Externí odkaz:
http://arxiv.org/abs/2410.14670
Sparse autoencoders have recently produced dictionaries of high-dimensional vectors corresponding to the universe of concepts represented by large language models. We find that this concept universe has interesting structure at three levels: 1) The "
Externí odkaz:
http://arxiv.org/abs/2410.19750
Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features represented in frontier models, it will be necessary to scale them up
Externí odkaz:
http://arxiv.org/abs/2410.08201
Recent work has proposed that language models perform computation by manipulating one-dimensional representations of concepts ("features") in activation space. In contrast, we explore whether some language model representations may be inherently mult
Externí odkaz:
http://arxiv.org/abs/2405.14860
We define and investigate the problem of $\textit{c-approximate window search}$: approximate nearest neighbor search where each point in the dataset has a numeric label, and the goal is to find nearest neighbors to queries within arbitrary label rang
Externí odkaz:
http://arxiv.org/abs/2402.00943
This paper studies density-based clustering of point sets. These methods use dense regions of points to detect clusters of arbitrary shapes. In particular, we study variants of density peaks clustering, a popular type of algorithm that has been shown
Externí odkaz:
http://arxiv.org/abs/2312.03940
Autor:
Meisburger, Nicholas, Lakshman, Vihan, Geordie, Benito, Engels, Joshua, Ramos, David Torres, Pranav, Pratik, Coleman, Benjamin, Meisburger, Benjamin, Gupta, Shubh, Adunukota, Yashwanth, Medini, Tharun, Shrivastava, Anshumali
Efficient large-scale neural network training and inference on commodity CPU hardware is of immense practical significance in democratizing deep learning (DL) capabilities. Presently, the process of training massive models consisting of hundreds of m
Externí odkaz:
http://arxiv.org/abs/2303.17727
We study the problem of $\textit{vector set search}$ with $\textit{vector set queries}$. This task is analogous to traditional near-neighbor search, with the exception that both the query and each element in the collection are $\textit{sets}$ of vect
Externí odkaz:
http://arxiv.org/abs/2210.15748
We present a new algorithm for the approximate near neighbor problem that combines classical ideas from group testing with locality-sensitive hashing (LSH). We reduce the near neighbor search problem to a group testing problem by designating neighbor
Externí odkaz:
http://arxiv.org/abs/2106.11565
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.