© 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
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
GPT2-SMALL · 5-ATT-KK · 19515 ｜ Neuronpedia
Home
Under Peer Review · Attention SAE Research Paper
GPT2-Small
Attention Out
5-ATT-KK
19515
Prev
Next
MODEL
5-att-kk
Source/SAE
INDEX
Go
Explanations
the word "or" in various contexts
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 5-att-kk
Configuration
ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_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
49,152
Data Type
float32
Hook Name
blocks.5.attn.hook_z
Hook Layer
5
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/5-att-kk/19515?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/5-att-kk/19515?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:
0.18
1:
0.20
2:
0.06
3:
0.06
4:
0.05
5:
0.17
6:
0.03
7:
0.04
8:
0.04
9:
0.03
10:
0.05
11:
0.06
Negative Logits
Pand
-2.01
Gast
-1.86
Oper
-1.85
Rad
-1.82
フォ
-1.82
Radio
-1.81
FI
-1.79
Mit
-1.78
Helic
-1.77
Tor
-1.74
POSITIVE LOGITS
�
2.55
�
2.13
�
1.94
asse
1.92
�
1.92
gered
1.88
�
1.87
reau
1.86
etimes
1.85
�
1.80
Act
ivations
Density 0.000%
Test
Steer
Stacked
Snippet
Full
Split DFA
Combine DFA
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
