Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
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
26738
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
references to municipal and corporate entities or structures
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
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/26738?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/26738?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
59
+0.14
0.8%
340
+0.14
0.8%
438
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
340
+0.14
0.03
126
+0.14
0.02
476
+0.13
0.03
Negative Logits
lessly
-1.79
tti
-1.63
*[
-1.53
rax
-1.51
lat
-1.50
roph
-1.47
rika
-1.45
ja
-1.45
roma
-1.42
ater
-1.41
POSITIVE LOGITS
¯
3.67
Ĭ
3.56
¿
3.56
ĺ
3.56
°
3.55
·¸
3.52
ļ
3.50
ĵ
3.48
ĩ
3.45
¤
3.45
Act
ivations
Density 0.228%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
