© 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 · 32098 ｜ Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
Residuals
2-RES-SM
32098
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
components and aspects related to coding and programming errors or configurations
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
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/32098?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/32098?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
111
+0.14
0.8%
459
+0.14
0.8%
319
+0.13
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
66
+0.14
0.04
386
+0.14
0.01
271
+0.13
-0.01
Negative Logits
ĵ
-3.01
«
-2.93
·¸
-2.88
¸
-2.82
¿½
-2.81
·
-2.79
Ĭ
-2.78
³
-2.70
ĥ½
-2.69
ĥ
-2.66
POSITIVE LOGITS
rails
1.78
orks
1.74
:=
1.68
parser
1.67
ayout
1.61
(@
1.61
inux
1.61
boolean
1.59
rand
1.58
-
1.58
Act
ivations
Density 0.270%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
