21

Intuitions for Tranformer Circuits (connorjdavis.com)

19 hours ago cjamsonhn connorjdavis.com

1

Language Modeling, Part 5: Reverse Engineering LSTM Cells (connorjdavis.substack.com)

a month ago cjamsonhn substack.com

2

Language Modeling Part 4: LSTMs (connorjdavis.substack.com)

a month ago cjamsonhn substack.com

1

Langauge Modeling, Part 3: Vanilla RNNs (connorjdavis.substack.com)

2 months ago cjamsonhn substack.com

1

Language Modeling, Part 2: Training Dynamics (connorjdavis.substack.com)

2 months ago cjamsonhn substack.com