Quintin’s Alignment Papers RoundupQuintin Pope10 Sep 2022 23:35 UTCQuintin’s alignment papers roundup—week 1Quintin Pope10 Sep 2022 6:39 UTC120 points6 comments9 min readLW linkQuintin’s alignment papers roundup—week 2Quintin Pope19 Sep 2022 13:41 UTC67 points2 comments10 min readLW linkQAPR 3: interpretability-guided training of neural netsQuintin Pope28 Sep 2022 16:02 UTC58 points2 comments10 min readLW linkQAPR 4: Inductive biasesQuintin Pope10 Oct 2022 22:08 UTC67 points2 comments18 min readLW linkQAPR 5: grokking is maybe not *that* big a deal?Quintin Pope23 Jul 2023 20:14 UTC114 points15 comments9 min readLW link