Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog/Podcast
NEW
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/Podcast
GitHub
Slack
Twitter
Contact
Home
Under Peer Review · Attention SAE Research Paper
GPT2-Small
Attention Out
0-ATT-KK
14033
Prev
Next
MODEL
0-att-kk
Source/SAE
INDEX
Go
Explanations
names of political figures
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 0-att-kk
Configuration
ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L0_Hcat_z_lr1.20e-03_l11.80e+00_ds24576_bs4096_dc1.00e-06_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.0.attn.hook_z
Hook Layer
0
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/0-att-kk/14033?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/0-att-kk/14033?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Head Attr Weights
0:
0.02
1:
0.18
2:
0.03
3:
0.17
4:
0.15
5:
0.16
6:
0.04
7:
0.05
8:
0.05
9:
0.04
10:
0.04
11:
0.03
Negative Logits
��
-3.70
�
-3.56
��
-3.54
friends
-3.52
�
-3.41
steps
-3.31
ById
-3.28
ァ
-3.28
��
-3.16
sites
-3.16
POSITIVE LOGITS
apter
4.39
olean
3.95
adan
3.85
vier
3.78
zzle
3.72
ars
3.71
ias
3.68
ar
3.68
adin
3.67
iter
3.65
Act
ivations
Density 0.002%
Test
Steer
Stacked
Snippet
Full
Split DFA
Combine DFA
Show Breaks
Hide Breaks
No Known Activations
