Sparse Autoencoders
Collection
SAEs are tools for understanding the internal representations of neural networks. These can be loaded using https://github.com/EleutherAI/sae
•
9 items
•
Updated
EleutherAI
non-profit
Verified
AI & ML interests
Large language models, scaling laws, AI Alignment, democratization of DL
Recent Activity
EleutherAI's activity
luciaquirke
updated
a
collection
1 day ago
Kyle1668
updated
a
dataset
2 days ago
Kyle1668
published
a
dataset
3 days ago
Kyle1668
updated
a
dataset
5 days ago
Kyle1668
published
a
dataset
5 days ago
craffel
authored
a
paper
5 days ago
norabelrose
updated
2
models
8 days ago
norabelrose
published
2
models
8 days ago
stellaathena
authored
a
paper
13 days ago
norabelrose
updated
a
model
16 days ago
norabelrose
published
a
model
16 days ago
norabelrose
updated
a
model
16 days ago
norabelrose
published
a
model
16 days ago
luciaquirke
updated
2
models
17 days ago
luciaquirke
updated
a
collection
17 days ago
luciaquirke
published
a
model
18 days ago