[Apart Lab](https://apartresearch.com/#Lab) collaborates with scholars in AI safety to publish technical research into safer and more aligned machine learning systems.

## Recent accepted papers from the Apart Lab

### Neuron to Graph: Interpreting Language Model Neurons at Scale

Alex Foote, Neel Nanda, Esben Kran, Ionnis Konstas, Shay Cohen, Fazl Barez

[Read paper](https://arxiv.org/abs/2305.19911 "‌") | [Visit project site](https://n2g.apartresearch.com/ "‌")

May 5, 2023  |  RTML workshop at ICLR 2023

### Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark

Jason Hoelscher-Obermaier, Julia Persson, Esben Kran, Ionnis Konstas, Fazl Barez

[Visit project site](https://specificityplus.apartresearch.com/ "‌")

July 10, 2023  |  ACL 2023

<p><a href="https://apartresearch.com/#Lab">Apart Lab</a> collaborates with scholars in AI&nbsp;safety to publish technical research into safer and more aligned machine learning systems.</p>
<h2 id="recent-accepted-papers-from-the-apart-lab">Recent accepted papers from the Apart Lab</h2>
<h3 id="neuron-to-graph-interpreting-language-model-neurons-at-scale">Neuron to Graph: Interpreting Language Model Neurons at Scale</h3>
<p>Alex Foote, Neel Nanda, Esben Kran, Ionnis Konstas,&nbsp;Shay Cohen, Fazl Barez</p>
<p><a title="‌" href="https://arxiv.org/abs/2305.19911">Read paper</a> |&nbsp;<a title="‌" href="https://n2g.apartresearch.com/">Visit project site</a></p>
<p>May 5, 2023&nbsp; |&nbsp; RTML&nbsp;workshop at ICLR 2023</p>
<h3 id="detecting-edit-failures-in-large-language-models-an-improved-specificity-benchmark">Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark</h3>
<p>Jason Hoelscher-Obermaier, Julia Persson, Esben Kran, Ionnis Konstas, Fazl Barez</p>
<p><a title="‌" href="https://specificityplus.apartresearch.com/">Visit project site</a></p>
<p>July 10, 2023&nbsp; |&nbsp; ACL 2023</p>
