Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Varma, Vikrant"'
Autor:
Lieberum, Tom, Rajamanoharan, Senthooran, Conmy, Arthur, Smith, Lewis, Sonnerat, Nicolas, Varma, Vikrant, Kramár, János, Dragan, Anca, Shah, Rohin, Nanda, Neel
Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse decomposition of a neural network's latent representations into seemingly interpretable features. Despite recent excitement about their potential, research applications outsi
Externí odkaz:
http://arxiv.org/abs/2408.05147
Autor:
Rajamanoharan, Senthooran, Lieberum, Tom, Sonnerat, Nicolas, Conmy, Arthur, Varma, Vikrant, Kramár, János, Nanda, Neel
Sparse autoencoders (SAEs) are a promising unsupervised approach for identifying causally relevant and interpretable linear features in a language model's (LM) activations. To be useful for downstream tasks, SAEs need to decompose LM activations fait
Externí odkaz:
http://arxiv.org/abs/2407.14435
Autor:
Rajamanoharan, Senthooran, Conmy, Arthur, Smith, Lewis, Lieberum, Tom, Varma, Vikrant, Kramár, János, Shah, Rohin, Nanda, Neel
Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We introduce the
Externí odkaz:
http://arxiv.org/abs/2404.16014
Autor:
Farquhar, Sebastian, Varma, Vikrant, Kenton, Zachary, Gasteiger, Johannes, Mikulik, Vladimir, Shah, Rohin
We show that existing unsupervised methods on large language model (LLM) activations do not discover knowledge -- instead they seem to discover whatever feature of the activations is most prominent. The idea behind unsupervised knowledge elicitation
Externí odkaz:
http://arxiv.org/abs/2312.10029
One of the most surprising puzzles in neural network generalisation is grokking: a network with perfect training accuracy but poor generalisation will, upon further training, transition to perfect generalisation. We propose that grokking occurs when
Externí odkaz:
http://arxiv.org/abs/2309.02390
Autor:
Shah, Rohin, Varma, Vikrant, Kumar, Ramana, Phuong, Mary, Krakovna, Victoria, Uesato, Jonathan, Kenton, Zac
The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a way that
Externí odkaz:
http://arxiv.org/abs/2210.01790
Agents should avoid unsafe behaviour during both training and deployment. This typically requires a simulator and a procedural specification of unsafe behaviour. Unfortunately, a simulator is not always available, and procedurally specifying constrai
Externí odkaz:
http://arxiv.org/abs/2201.08102
Autor:
Abramson, Josh, Ahuja, Arun, Barr, Iain, Brussee, Arthur, Carnevale, Federico, Cassin, Mary, Chhaparia, Rachita, Clark, Stephen, Damoc, Bogdan, Dudzik, Andrew, Georgiev, Petko, Guy, Aurelia, Harley, Tim, Hill, Felix, Hung, Alden, Kenton, Zachary, Landon, Jessica, Lillicrap, Timothy, Mathewson, Kory, Mokrá, Soňa, Muldal, Alistair, Santoro, Adam, Savinov, Nikolay, Varma, Vikrant, Wayne, Greg, Williams, Duncan, Wong, Nathaniel, Yan, Chen, Zhu, Rui
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial agents that
Externí odkaz:
http://arxiv.org/abs/2012.05672