INDEX

Explanations

phrases indicating agreement or consent

oai_token-act-pair · gpt-3.5-turbo

instances of consensus or agreement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oufl

-0.77

vas

-0.70

crow

-0.68

 Tycoon

-0.67

esa

-0.66

 Blooming

-0.65

agin

-0.65

asus

-0.64

 glands

-0.63

omial

-0.63

POSITIVE LOGITS

 unanimously

1.00

 agreement

0.80

reements

0.78

ipeg

0.77

 agreeing

0.76

 agre

0.74

reement

0.74

ettle

0.73

agree

0.73

rences

0.73

Activations Density 0.038%

phrases indicating agreement or consent

instances of consensus or agreement

No Comments

No Known Activations