-
Ran this from the demo code:
```
import os
# Check if we're in Colab
try:
import google.colab # noqa: F401 # type: ignore
in_colab = True
except ImportError:
in_colab = False
…
-
Thank you for your outstanding research. However, it seems that I am unable to find the paper at the moment. Could you kindly provide it? Thank you.
-
I am trying your model in this link {https://github.com/jadhavhninad/Sparse_autoencoder/blob/master/se_keras4.py}
It gives me *(NAN) or very high loss
Any advise ?
-
excuse me,i would like to know why I got ---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
Cell …
-
### Suggestion / Feature Request
Been curious for awhile now, then moreso since reading Disentangling Dense Embeddings with Sparse Autoencoders (https://arxiv.org/html/2408.00657v2)
It looks like …
-
[this issue is migrated from a previous version of the repo]
@elephantmipt and @zdaiot ask:
Hi, thank you for releasing great tool! It would be great if you provide more details on which files…
-
# Sparse Autoencoders for a More Interpretable RLHF | Naomi Bashkansky
Extending Anthropic's recent monosemanticity results toward a new, more interpretable way to fine-tune.
[https://naomibashkansk…
-
Did you find any paper or did you do any empirical experiment that proves that simply adding l1 loss to hidden representation encourages sparsity on the hidden representation
-
Right now, the library considers MLP as atomic blocks - which is fine. However, with SAE, we can decompose these into a smaller number of interpretable features. The SAE approach is a little sensitive…
-
Since the release of torch 2.2.0, there is no "params_t" anymore, meaning you get the following error, since the requirements of the pyproject.toml are torch=">=2.1.2".
```
[/usr/local/lib/python…