TY - RPRT ID - dl-20-1 TI - Toy Models of Superposition AU - Elhage, Nelson AU - Hume, Tristan AU - Olsson, Catherine AU - Schiefer, Nicholas AU - Henighan, Tom AU - Kravec, Shauna AU - Hatfield-Dodds, Zac AU - Lasenby, Robert AU - Drain, Dawn AU - Chen, Carol AU - Grosse, Roger AU - McCandlish, Sam AU - Kaplan, Jared AU - Amodei, Dario AU - Wattenberg, Martin AU - Olah, Christopher PB - Transformer Circuits Thread PY - 2022 UR - https://transformer-circuits.pub/2022/toy_model/toy_model.pdf ER - TY - CONF ID - dl-20-2 TI - Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations AU - Locatello, Francesco AU - Bauer, Stefan AU - Lucic, Mario AU - Rätsch, Gunnar AU - Gelly, Sylvain AU - Schölkopf, Bernhard AU - Bachem, Olivier T2 - Proceedings of the 36th International Conference on Machine Learning PY - 2019 UR - https://proceedings.mlr.press/v97/locatello19a.html ER - TY - CONF ID - dl-20-3 TI - Sanity Checks for Saliency Maps AU - Adebayo, Julius AU - Gilmer, Justin AU - Muelly, Michael AU - Goodfellow, Ian AU - Hardt, Moritz AU - Kim, Been T2 - Advances in Neural Information Processing Systems 31 PY - 2018 UR - https://proceedings.neurips.cc/paper/2018/hash/294a8ed24b1ad22ec2e7efea049b8737-Abstract.html ER -