INDEX

Explanations

phrases indicating uncertainty or doubt followed by questions or inquiries

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate questioning or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

otti

-0.70

DIV

-0.70

kee

-0.67

ONG

-0.65

velop

-0.65

IUM

-0.65

STDOUT

-0.64

ena

-0.62

ario

-0.61

iva

-0.61

POSITIVE LOGITS

 whether

1.95

why

1.66

whether

1.46

WHY

1.35

how

1.33

why

1.29

 whence

1.23

 what

1.17

 Whether

1.12

Whether

1.05

Activations Density 0.257%

phrases indicating uncertainty or doubt followed by questions or inquiries

phrases that indicate questioning or uncertainty

No Comments

No Known Activations