INDEX

Explanations

questions and statements indicating uncertainty or speculation

oai_token-act-pair · gpt-3.5-turbo

rhetorical questions and expressions of doubt or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arde

-0.73

İĭ

-0.69

isin

-0.67

ronics

-0.66

anwhile

-0.65

 angered

-0.65

drawn

-0.63

 cumbers

-0.62

 contag

-0.62

 buildup

-0.61

POSITIVE LOGITS

yes

1.91

yes

1.78

YES

1.70

Yes

1.70

Yes

1.65

YES

1.60

Absolutely

1.56

 Nope

1.48

 Absolutely

1.39

Yep

1.23

Activations Density 0.629%

questions and statements indicating uncertainty or speculation

rhetorical questions and expressions of doubt or uncertainty

No Comments

No Known Activations