391 citations · 1.6k across the 16 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024★ 2 cited
Sabotage Evaluations for Frontier Models
Joe Benton, Misha Wagner, Eric Christiansen +13
Sufficiently capable models could subvert human oversight and decision-making in important contexts. For example, in the context of AI development, models could covertly sabotage e…
cs.LG2022★ 48 cited
Toy Models of Superposition
Nelson Elhage, Tristan Hume, Catherine Olsson +13
Neural networks often pack many unrelated concepts into a single neuron - a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. This…