Quintin’s Alignment Papers RoundupQuintin PopeSep 10, 2022, 11:35 PMQuintin’s alignment papers roundup—week 1Quintin PopeSep 10, 2022, 6:39 AM120 points6 comments9 min readLW linkQuintin’s alignment papers roundup—week 2Quintin PopeSep 19, 2022, 1:41 PM67 points2 comments10 min readLW linkQAPR 3: interpretability-guided training of neural netsQuintin PopeSep 28, 2022, 4:02 PM58 points2 comments10 min readLW linkQAPR 4: Inductive biasesQuintin PopeOct 10, 2022, 10:08 PM67 points2 comments18 min readLW linkQAPR 5: grokking is maybe not *that* big a deal?Quintin PopeJul 23, 2023, 8:14 PM114 points15 comments9 min readLW link