INDEX

Explanations

website loading indicators

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Loading"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.80

atively

-0.80

imposed

-0.75

ulation

-0.71

uay

-0.69

tesy

-0.69

stood

-0.69

ule

-0.69

kaya

-0.67

ties

-0.67

POSITIVE LOGITS

 Loading

1.17

 Advertisement

0.92

artifacts

0.83

 VIDEOS

0.81

 guiActive

0.81

 Header

0.78

 Thumbnails

0.76

gallery

0.75

 Transcript

0.73

 Empty

0.73

Activations Density 0.010%

website loading indicators

instances of the word "Loading"

No Comments

No Known Activations