Neuronpedia is amazing! Thank you for building this

Open Source Interpretability Platform and Tools

Interpretability (the understanding of AI internals) is an unsolved problem - especially with the speed of its advancing capabilities, and the new architectures/developments being released every month.

Is interpretability needed? While it's possible that advanced AI is somehow "naturally aligned" to be pro-human and pro-Earth, there's no benefit to assuming that this is true. It seems unlikely that all advanced AI would be *fully* aligned in all the possible scenarios and edge cases.

Neuronpedia's role is to accelerate understanding of AI models, so that when they get powerful enough, we have a better chance of aligning them. If we can increase the probability of a good outcome by even 0.01%, that's an expected value of saving many, many current and future lives - certainly a worthwhile and meaningful endeavor.

Check out our [announcement post](https://www.neuronpedia.org/blog/neuronpedia-is-now-open-source) for the details.

Code, issues, documentation available at our [Github](https://github.com/hijohnnylin/neuronpedia).

4TB+ in data available at our [Public Datasets](https://neuronpedia-datasets.s3.us-east-1.amazonaws.com/index.html?prefix=v1/).

Decode: Neuronpedia, SAELens, and more

1067431123

1435915265

148788709

2074652487

2352003526

2535103040

2547000601

2551237796

2595251256

2808155606

2883383521

2970598858

3107677517

316638097

339774024

3497063662

3797661376

3868271524

410756082

4124487947

4172451122

496574456

698107245

91415239

2729980760

3440869557

671754822

87081813

1014384873

1112422858

153399038

2028390811

220342792

2266630408

2456389719

2519810400

2539558839

2826465835

We are a nonprofit, so instead of charging fees we rely on the generosity of donors like you.

Choose a donation for Every.org

2843798242

2898624300

2916352438

3125568929

3259439560

3583328878

3642494300

3902459442

4136002033

4177183036

4250940449

585491400

641510716

91682487