© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
Home
OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
GPT2-Small
Residual Post - 32k
10-RES_POST_32K-OAI
31240
Prev
Next
MODEL
10-res_post_32k-oai
Source/SAE
INDEX
Go
Explanations
references to programming concepts and structures, particularly related to data types and operations
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 10-res_post_32k-oai
Configuration
jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
32,768
Data Type
torch.float32
Hook Name
blocks.10.hook_resid_post
Hook Layer
10
Architecture
standard
Context Size
64
Dataset
Skylion007/openwebtext
Activation Function
topk
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gpt2-small/10-res_post_32k-oai/31240?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/10-res_post_32k-oai/31240?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
585
+0.12
0.5%
373
+0.10
0.5%
618
+0.09
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
326
+0.12
0.05
530
+0.10
0.02
701
+0.09
0.02
Negative Logits
ãĥĹ
-0.73
apers
-0.72
505
-0.68
Ellison
-0.67
ebus
-0.66
304
-0.65
enser
-0.64
031
-0.63
FTWARE
-0.63
324
-0.63
POSITIVE LOGITS
ii
1.14
Jord
0.96
ii
0.96
j
0.93
II
0.91
JR
0.89
II
0.87
jad
0.87
J
0.86
Manga
0.80
Act
ivations
Density 0.373%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations