Bibliography (7):

1. https://github.com/google-deepmind/alta

2. Attention Is All You Need

3. RASP: Thinking Like Transformers

4. Tracr: Compiled Transformers as a Laboratory for Interpretability

5. Universal Transformers

6. Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks

7. ​ ‘end-to-end’ directory