© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
MAY 26
Assistant Axis
JAN 26
Circuit Tracer
APR 26
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
Docs
Community
Blog
Privacy & Terms
Contact
Sign In
GPT2-SMALL · 10-ATT-KK · 6823 ｜ Neuronpedia
Home
Under Peer Review · Attention SAE Research Paper
GPT2-Small
Attention Out
10-ATT-KK
6823
Prev
Next
MODEL
10-att-kk
Source/SAE
INDEX
Go
Explanations
references to civilian casualties and military actions
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 10-att-kk
Configuration
ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
24,576
Data Type
float32
Hook Name
blocks.10.attn.hook_z
Hook Layer
10
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
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/gpt2-small/10-att-kk/6823?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/gpt2-small/10-att-kk/6823?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Head Attr Weights
0:
0.04
1:
0.03
2:
0.03
3:
0.20
4:
0.03
5:
0.14
6:
0.07
7:
0.05
8:
0.13
9:
0.11
10:
0.08
11:
0.03
Negative Logits
–
-3.73
––
-3.72
—-
-3.19
————
-3.10
··
-3.09
―
-2.99
——
-2.88
—"
-2.81
)—
-2.80
.–
-2.75
POSITIVE LOGITS
organisers
3.54
ideshow
3.46
...
3.39
".
3.30
Mr
3.26
',"
3.24
Mr
3.19
''.
3.18
`.
3.05
Nasa
3.00
Act
ivations
Density 0.089%
Test
Steer
Stacked
Snippet
Full
Split DFA
Combine DFA
Show Breaks
Hide Breaks
No Known Activations
