Neuronpedia
Get Started
API
SAE Evals
Releases
Jump To
Search
Models
Evals
Steer
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Twitter
Contact
Home
Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
GPT2-Small
Residual Stream
10-RES-JB
16915
Prev
Next
MODEL
10-res-jb
SAE
INDEX
Go
Explanations
time-related events and instances of spatial relationships
oai_token-act-pair · gpt-3.5-turbo
No Scores
phrases that indicate time and relational dynamics in experiences
oai_token-act-pair · gpt-4o-mini
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-sonnet-20240620
Generate
Features by Cosine Similarity
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
24,576
Data Type
torch.float32
Hook Point
blocks.10.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
10
Activation Function
relu
Show All
Embeds
Plots
Explanation
