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