INDEX

Explanations

Loading messages with different levels of intensity

oai_token-act-pair · gpt-3.5-turbo

instances of loading messages or indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hips

-0.90

atively

-0.72

stood

-0.70

beit

-0.68

ially

-0.66

ial

-0.66

metic

-0.64

folk

-0.64

ror

-0.62

rition

-0.62

POSITIVE LOGITS

 Loading

0.85

Screen

0.75

 guiName

0.73

 Thumbnails

0.71

 Rooms

0.69

 Bagg

0.68

 Countries

0.65

 Load

0.64

 ERROR

0.64

 Content

0.64

Activations Density 0.014%

Loading messages with different levels of intensity

instances of loading messages or indicators

No Comments

No Known Activations