hannamw

ACT-Thor

Code Release for the COLING 2022 Paper ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments

dictionary_learning

copy of dictionary_learning for use with garden path experiments

eacl-tutorial-resources

A repo containing resources for the EACL 2023 tutorial "Transformer-Specific Interpretability"

EAP-IG

eap-ig-faithfulness

Code for "Automatic Circuit Finding and Faithfulness"

feature-circuits-gp

GP-mechanisms

gpt2-greater-than

Code Release for the 2023 NeurIPS Paper How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

hannamw.github.io

My personal website

incremental_parse_probe

an incremental parse probe for other models

hannamw/EAP-IG

hannamw/eap-ig-faithfulness

Code for "Automatic Circuit Finding and Faithfulness"

hannamw/gpt2-greater-than

Code Release for the 2023 NeurIPS Paper How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

hannamw/ACT-Thor

Code Release for the COLING 2022 Paper ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments

hannamw/othello-in-c

The game Othello, written in C. Play against another player or a computer of varying difficulties. Or, watch two computers play!

hannamw/dictionary_learning

copy of dictionary_learning for use with garden path experiments

hannamw/eacl-tutorial-resources

A repo containing resources for the EACL 2023 tutorial "Transformer-Specific Interpretability"

hannamw/feature-circuits-gp

hannamw/hannamw.github.io

My personal website

hannamw/incremental_parse_probe

an incremental parse probe for other models

hannamw/learn-hangul

hannamw/lms-in-love

hannamw/probed-information

All of the code needed to replicate the 2023 EACL paper "The Functional Relevance of Probed Information: A Case Study"

hannamw/TransformerLens

A library for mechanistic interpretability of GPT-style language models