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
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
Residuals
1-RES-SM
27010
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
references to specific conditions in contractual agreements
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
Configuration
ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
How To Load
Prompts (Dashboard)
32,768 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
32,768
Data Type
torch.float32
Hook Name
blocks.1.hook_resid_post
Hook Layer
1
Architecture
standard
Context Size
128
Dataset
EleutherAI/the_pile_deduplicated
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/pythia-70m-deduped/1-res-sm/27010?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/1-res-sm/27010?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
502
+0.12
0.7%
471
+0.11
0.6%
260
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
431
+0.12
0.02
471
+0.11
0.02
502
+0.10
0.02
Negative Logits
½
-3.88
ĥ½
-3.83
»
-3.74
ı
-3.66
»¿
-3.57
·¸
-3.55
¿½
-3.53
Ń
-3.51
´
-3.43
<|outofrange|>
-3.38
POSITIVE LOGITS
ensory
2.09
ending
1.82
("
1.77
burg
1.72
[^
1.67
(“
1.65
hips
1.64
{#
1.60
,[
1.58
cias
1.56
Act
ivations
Density 0.049%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
