SAE post

posts/biblio.bib

@@ -280,4 +280,31 @@ @misc{cui2024orbenchoverrefusalbenchmarklarge
       archivePrefix={arXiv},
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2405.20947}, 
+}
+
+@misc{bloom2024gpt2residualsaes,
+   title = {Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2 Small},
+   author = {Joseph Bloom},
+   year = {2024},
+   howpublished = {\url{https://www.alignmentforum.org/posts/f9EgfLSurAiqRJySD/open-source-sparse-autoencoders-for-all-residual-stream}},
+}
+
+@misc{lieberum2024gemmascopeopensparse,
+      title={Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2}, 
+      author={Tom Lieberum and Senthooran Rajamanoharan and Arthur Conmy and Lewis Smith and Nicolas Sonnerat and Vikrant Varma and János Kramár and Anca Dragan and Rohin Shah and Neel Nanda},
+      year={2024},
+      eprint={2408.05147},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2408.05147}, 
+}
+
+@misc{thompson2024flrtfluentstudentteacherredteaming,
+      title={FLRT: Fluent Student-Teacher Redteaming}, 
+      author={T. Ben Thompson and Michael Sklar},
+      year={2024},
+      eprint={2407.17447},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2407.17447}, 
 }