Pinned Repositories
activationsteering
ARENA_2.0
automated-interpretability
awesome-colab-notebooks
Collection of google colaboratory notebooks for fast and easy experiments
awesome-mech-interp
An awesome curated list of resources dedicated to Mechanistic interpretability
basic-scripts
a bunch of basic scripts hacked together but working and are maybe useful for me
firstuserhere.github.io
gpt4Vadvanced
Testing GPT-4 Vision on Advanced examination questions (2023) across physics, chemistry, and mathematics
hackathon-attention-superposition
interp-hackathon-layernorm
Investigating the 4.39 problem from Concrete Open Problems
firstuserhere's Repositories
firstuserhere/hackathon-attention-superposition
firstuserhere/firstuserhere.github.io
firstuserhere/gpt4Vadvanced
Testing GPT-4 Vision on Advanced examination questions (2023) across physics, chemistry, and mathematics
firstuserhere/awesome-mech-interp
An awesome curated list of resources dedicated to Mechanistic interpretability
firstuserhere/interp-hackathon-layernorm
Investigating the 4.39 problem from Concrete Open Problems
firstuserhere/multimodal-mechinterp
Basic mech interp analysis for some multimodal models
firstuserhere/activationsteering
firstuserhere/ARENA_2.0
firstuserhere/automated-interpretability
firstuserhere/awesome-colab-notebooks
Collection of google colaboratory notebooks for fast and easy experiments
firstuserhere/basic-scripts
a bunch of basic scripts hacked together but working and are maybe useful for me
firstuserhere/firstuserhere
Config files for my GitHub profile.
firstuserhere/gpt-manifold
Forking to add functionality for automated betting
firstuserhere/IF
firstuserhere/manifold
Manifold Markets: A market for every question
firstuserhere/GPU-Puzzles
Solve puzzles. Learn CUDA.
firstuserhere/Improved-worldmodels
Critiques of the pre-print, suggestions for improvement, and counterfactual examples testing
firstuserhere/jsonformer
A Bulletproof Way to Generate Structured JSON from Language Models
firstuserhere/LLaVA-mechinterp
firstuserhere/Megatron-LM
Ongoing research training transformer models at scale
firstuserhere/miras-sudoku-solution
Fork of a possible solution for testing
firstuserhere/nanogenmo
National Novel Generation Month, 2023 edition.
firstuserhere/practiceCUDA
firstuserhere/replications
My attempts at replicating results of papers
firstuserhere/sparse_autoencoder
Sparse Autoencoder for Mechanistic Interpretability
firstuserhere/SPARta
LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
firstuserhere/tinystories
Reproduction of TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
firstuserhere/visual-chatgpt
VisualChatGPT
firstuserhere/weak-to-strong
firstuserhere/Whisper-mechinterp
Mechanistic Interpretability for Whisper