© 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
PYTHIA-70M-DEDUPED · 4-RES-SM · 13700 ｜ Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
Residuals
4-RES-SM
13700
Prev
Next
MODEL
4-res-sm
Source/SAE
INDEX
Go
Explanations
personal experiences related to illness or health-related challenges
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/4-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.4.hook_resid_post
Hook Layer
4
Architecture
standard
Context Size
128
Dataset
EleutherAI/the_pile_deduplicated
Activation Function
relu
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/pythia-70m-deduped/4-res-sm/13700?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/pythia-70m-deduped/4-res-sm/13700?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
280
+0.24
1.8%
21
+0.23
1.8%
397
+0.22
1.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
111
+0.24
0.17
156
+0.23
0.16
71
+0.22
0.12
Negative Logits
Loading
-1.45
aisle
-1.35
Register
-1.31
atsu
-1.30
bye
-1.30
ansas
-1.28
lickr
-1.27
âĸ
-1.27
umab
-1.24
ypse
-1.21
POSITIVE LOGITS
º
2.73
·
2.69
¢
2.60
»
2.57
°
2.55
ļ
2.51
ĺ
2.51
¶
2.50
±
2.49
¹
2.49
Act
ivations
Density 1.101%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
