© 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 · 1-RES-SM · 28235 ｜ Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
Residuals
1-RES-SM
28235
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
instances of punctuation or formatting characters
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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/pythia-70m-deduped/1-res-sm/28235?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/1-res-sm/28235?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
344
+0.17
0.9%
306
+0.13
0.7%
60
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
91
+0.17
0.00
366
+0.13
0.00
39
+0.13
0.00
Negative Logits
ĥ
-2.73
©
-2.64
«
-2.28
Ĥ
-2.04
ģ
-2.03
°
-2.01
Ī
-1.95
¥
-1.82
Ķ
-1.82
¡
-1.82
POSITIVE LOGITS
idade
1.52
oret
1.47
noreply
1.43
wand
1.43
oth
1.41
odor
1.38
CRT
1.38
ῦ
1.34
lessness
1.31
WHO
1.30
Act
ivations
Density 0.001%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
