-
Just curious if anyone is thinking about implementing a training pipeline for JumpReLU SAEs! They have a couple of properties which are really desirable for something I'm working on.
-
Is this out of scope? I hope not, would be nice to have a one-stop shop for interpretability tooling.
### Proposal
It should be easy to get the most bare-bones interpretability research off the…
-
### Describe the bug
I have a **configuration with multiple SSIDs (3) on one wireless radio**, everything works fine on 80Mhz.
When I change from 80Mhz to 160Mhz all those wireless SSIDs on 5GHZ…
-
Hi. Does anyone know how to get weights like these?
I'm trying to follow this tutorial
http://ufldl.stanford.edu/wiki/index.php/Visualizing_a_Trained_Autoencoder
and to get the same results with thi…
-
AssertionError: If encoder isn't an AutoEncoder, it should have weights 'W_enc', 'W_dec', 'b_enc', 'b_dec'
Gated SAE do not have b_enc and it seems AutoEncoder is not suitable for gated SAE.
-
Hi!
Im using following code to send an empty 128 byte ISO 14230 K-Line message:
Problem is that this takes more than 760ms to send!!
And thus a high DefaultTxTimeout is necessary
The read is ab…
-
### Background and motivation
Intel has announced the features available in the next version of `Avx10 `(10.2). In order to support this, .NET needs to expand the `Avx10 `library to include the new A…
-
Our current approach embeds datasets using Sentence Transformers that give us one embedding per "chunk" of text (so if we pass in 500 tokens of text or 100 tokens of text we always get 1 embedding). S…
-
-
Hi, while executing:
`torchrun --nproc_per_node gpu -m sae meta-llama/Meta-Llama-3-8B --distribute_modules --batch_size 1 --layers 24 25 --grad_acc_steps 8 --ctx_len 2048 --k 192 --load_in_8bit --mic…