Locking activations via k-sparse autoencoders.
Project description
Locking_Backdoors_Via_Steering_Language_Models
Suppresses backdoors in reward models, by locking to base models.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file locking_activations-0.1.0.tar.gz.
File metadata
- Download URL: locking_activations-0.1.0.tar.gz
- Upload date:
- Size: 2.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | b6f3e7562fdbfa07f370499a9fb846cfa25556625d49cb210f0c1f9ced1ba6db |
|
| MD5 | b6269841311c808e6e6e33b1b83f15f5 |
|
| BLAKE2b-256 | 9d0b9c0c62902debdcd1a0cfc5ee266624bdd2d3a5c68d4ca9105ae96fa45a0b |
File details
Details for the file locking_activations-0.1.0-py3-none-any.whl.
File metadata
- Download URL: locking_activations-0.1.0-py3-none-any.whl
- Upload date:
- Size: 2.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 115407effbe28e779a3252cd260acd7d47f3073ec4d0f490078ee9cb91bb5b0d |
|
| MD5 | 8a41b1e89cba2a0bd7857bd1081c5f08 |
|
| BLAKE2b-256 | c699928f31b721096f5d9f0405d22489bd44a2eecccc341266dc9f969493c791 |
