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
26888
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
references to choices or options
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/26888?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/26888?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
300
+0.12
0.7%
478
+0.12
0.6%
447
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
35
+0.12
0.02
511
+0.12
0.03
447
+0.11
0.03
Negative Logits
Ħ
-3.55
ľĵ
-3.44
ĺ
-3.40
¢
-3.38
ĻĤ
-3.37
Īĺ
-3.36
£
-3.33
º
-3.33
¡
-3.29
Ń
-3.27
POSITIVE LOGITS
deal
1.63
chid
1.52
else
1.51
`.
1.51
acity
1.49
inda
1.48
.'"
1.46
ações
1.45
acles
1.45
leans
1.45
Act
ivations
Density 0.511%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
