INDEX

Explanations

URLs in text

oai_token-act-pair · gpt-3.5-turbo

URLs and web addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ĺħ

-0.75

 taxp

-0.73

etheless

-0.73

 overshadow

-0.71

 conclud

-0.69

 Moody

-0.68

©¶æ

-0.67

 Morse

-0.66

gdala

-0.65

 Labrador

-0.65

POSITIVE LOGITS

www

1.67

natureconservancy

1.29

localhost

1.21

://

1.17

www

1.12

forum

1.12

archive

1.11

past

1.10

goo

1.06

youtu

1.03

Activations Density 0.018%

URLs in text

URLs and web addresses

No Comments

No Known Activations