INDEX

Explanations

the phrase "the main."

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the main story or important content in a document

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

 Centauri

-0.80

»Ĵ

-0.72

 Profession

-0.70

 Metallic

-0.69

 Benefit

-0.69

Ö¼

-0.67

NetMessage

-0.66

utenant

-0.66

ï¸ı

-0.66

 Sparrow

-0.63

POSITIVE LOGITS

stay

0.84

 theme

0.79

 source

0.78

ideshow

0.75

 story

0.73

 cartoons

0.72

 cartoon

0.70

 slideshow

0.69

 gallery

0.67

stuff

0.67

Activations Density 0.016%

the phrase "the main."

phrases indicating the main story or important content in a document

No Comments

No Known Activations