Pinned Repositories
nnsight
The nnsight package enables interpreting and manipulating the internals of deep learned models.
2024_dtl_lm-interpretability
Textbook for the NYU Digital Theory Lab's Introduction to Interpretability for Language Models (Summer 2024)
ACORN
ACORN, an analog document-term matrix from the 1960s
bad_ocr_embedding_test
A quick test of an LLM's robustness to OCR errors.
hOCRpy
Parsing and analyzing hOCR data
homespun_nlp
Revisiting the core formalisms of NLP
lm_probe
Train linear probes on neural language models
polaroid_stopped
Removing all the stopwords from Clark Coolidge's _Polaroid_
tylershoemaker.info
Personal website
vec2text
utilities for decoding deep representations (like sentence embeddings) back to text
t-shoemaker's Repositories
t-shoemaker/2024_dtl_lm-interpretability
Textbook for the NYU Digital Theory Lab's Introduction to Interpretability for Language Models (Summer 2024)
t-shoemaker/bad_ocr_embedding_test
A quick test of an LLM's robustness to OCR errors.
t-shoemaker/engl54_visit
t-shoemaker/ACORN
ACORN, an analog document-term matrix from the 1960s
t-shoemaker/hOCRpy
Parsing and analyzing hOCR data
t-shoemaker/homespun_nlp
Revisiting the core formalisms of NLP
t-shoemaker/polaroid_stopped
Removing all the stopwords from Clark Coolidge's _Polaroid_
t-shoemaker/tylershoemaker.info
Personal website