How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model.
Michael HannaOllie LiuAlexandre VariengienPublished in: NeurIPS (2023)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- document retrieval
- training data
- probabilistic model
- speech recognition
- retrieval model
- ad hoc information retrieval
- query expansion
- information retrieval
- training examples
- language modelling
- test collection
- smoothing methods
- mixture model
- decision trees
- context sensitive
- computer vision
- translation model
- neural network
- maximum likelihood
- machine translation
- relevance model