Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
GPT2-Small
Residual Stream
12-RES-JB
7003
Prev
Next
MODEL
12-res-jb
Source/SAE
INDEX
Go
Explanations
names mentioned in an online conversation or forum format
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
No Scores
references to dates and personal identifiers
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 12-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
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.11.hook_resid_post
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
11
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/12-res-jb/7003?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/12-res-jb/7003?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
ÂŃ
-2.11
–
-1.42
âĢ³
-1.40
âĢIJ
-1.29
ÂŃ
-1.17
—
-1.17
âĢ²
-1.08
âĪĴ
-0.99
Isis
-0.94
–
-0.92
POSITIVE LOGITS
...
2.35
,...
2.30
....
2.11
...?
2.09
..."
2.01
"...
1.99
......
1.98
.....
1.94
.......
1.92
--
1.89
Act
ivations
Density 0.467%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
