From 3c6b13ac75813db15d9bab9de222e98d65c2eedc Mon Sep 17 00:00:00 2001 From: Liam Date: Fri, 1 Nov 2024 12:26:55 -0400 Subject: [PATCH] Improve steering UX --- viz/src/components/CustomSeqPlayground.tsx | 120 ++++++++++++--------- 1 file changed, 67 insertions(+), 53 deletions(-) diff --git a/viz/src/components/CustomSeqPlayground.tsx b/viz/src/components/CustomSeqPlayground.tsx index 3b1efd4..6370d6f 100644 --- a/viz/src/components/CustomSeqPlayground.tsx +++ b/viz/src/components/CustomSeqPlayground.tsx @@ -206,74 +206,88 @@ const CustomSeqPlayground = ({ feature }: CustomSeqPlaygroundProps) => { href="https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html#appendix-methods-steering" className="underline" > - their implementation + their approach , we reconstruct the input sequence with the SAE "spliced into" ESM2 at layer 24. With steering multiplier N, the SAE activation at every residue in the sequence is set to N * (max activation along the sequence). So,

- Check out{" "} - - this explanation - {" "} - from Anthropic for more technical details. We're experimenting with different - methods of steering and will make them available soon! + We're experimenting with different methods of steering and will make them available + soon!

-
- - Steer multiplier: {steerMultiplier} - -
- setSteerMultiplier(value[0])} - /> +
+
+
+ + Steer multiplier: {steerMultiplier} + + setSteerMultiplier(value[0])} + className="flex-grow" + /> +
+ +
+ + + + +
+ + {/* Steer button */} +
- -
- {steeredActivations.length > 0 && ( - <> -
- 0 && ( + <> +
+ +
+ -
- - - )} + + )} +
)}