Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/RSS
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
GPT2-Small
Residual Stream
5-RES-JB
6066
Prev
Next
MODEL
5-res-jb
Source/SAE
INDEX
Go
Explanations
phrases related to critical commentary or negative viewpoints
oai_token-act-pair · gpt-3.5-turbo
No Scores
expressions of sentiment or opinion, especially negative emotions related to events or situations
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-sonnet-20240620
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 5-res-jb
Configuration
jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
5
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/5-res-jb/6066?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/5-res-jb/6066?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
?).
-0.85
.).
-0.74
etheless
-0.74
.*
-0.69
+.
-0.66
.)
-0.66
).
-0.64
arthed
-0.61
odox
-0.61
arist
-0.60
POSITIVE LOGITS
,"
1.13
%"
1.07
[
1.07
.,"
0.92
",
0.92
":
0.91
,'"
0.89
,''
0.85
"]
0.83
"
0.82
Act
ivations
Density 0.740%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
