Toolkit for running toy models of superposition experiments
Project description
TMS
Codebase for quickly implementing experiments with toy models of superposition.
Quickstart
To set up the environment, see setup docs for detailed instructions.
To reproduce figures from Anthropic's Toy Models of Superposition, see sample script
Acknowledgements
This codebase is heavily adapted from the ARENA 3.0 codebase, designed and maintained by Callum McDougall. Many thanks to Callum and the ARENA team!
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tms_kit-0.4.1.tar.gz
(25.7 kB
view details)
Built Distribution
tms_kit-0.4.1-py3-none-any.whl
(27.7 kB
view details)
File details
Details for the file tms_kit-0.4.1.tar.gz.
File metadata
- Download URL: tms_kit-0.4.1.tar.gz
- Upload date:
- Size: 25.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 92d6cca5753ca4bd90c54a2b2dc1d20572e24246c6a4a5d54aed62bdfb203f7e |
|
| MD5 | 09643e732930fca65c5e9540fe19545f |
|
| BLAKE2b-256 | 28b7e73dbf2b12c666ec39a713513ca25e6b55ef3f7afaf60820a122827e6f18 |
File details
Details for the file tms_kit-0.4.1-py3-none-any.whl.
File metadata
- Download URL: tms_kit-0.4.1-py3-none-any.whl
- Upload date:
- Size: 27.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 94b63bccd77877910bedaa4274fb0e6aaddb74465ea70f1d03a386d700cdef82 |
|
| MD5 | 1c145c901f38035220d5c65158265204 |
|
| BLAKE2b-256 | a1becfa1982c52486cfea9f014a2e766d9a764eae532a53c9926a71a6f23fd4c |
