© 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 · 2-RES-SM · 27688 ｜ Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
Residuals
2-RES-SM
27688
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
terms related to legal and forensic contexts
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/2-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.2.hook_resid_post
Hook Layer
2
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/2-res-sm/27688?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/2-res-sm/27688?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
76
+0.14
0.8%
146
+0.13
0.8%
47
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
146
+0.14
0.09
76
+0.13
0.07
440
+0.12
0.07
Negative Logits
ĻĤ
-3.54
ł
-3.26
-3.22
↵↵
-3.22
↵
-3.22
-3.22
-3.22
↵ ↵
-3.22
↵↵
-3.22
↵
-3.22
POSITIVE LOGITS
throat
1.54
mism
1.41
ades
1.37
planted
1.36
palate
1.32
ylvania
1.30
thrown
1.30
ede
1.27
ectomy
1.26
dumped
1.26
Act
ivations
Density 3.292%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
