INDEX

Explanations

phrases related to editorial content and media personalities within a specific niche

oai_token-act-pair · gpt-3.5-turbo

mentions of various media outlets and publications

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

 federally

-0.77

bestos

-0.76

 costly

-0.69

pard

-0.67

 compounds

-0.66

 stranded

-0.65

lyak

-0.64

 withdrawn

-0.64

Bei

-0.63

mop

-0.63

POSITIVE LOGITS

 Editorial

1.24

 Editors

1.22

 Weekly

1.20

 Editor

1.18

 Podcast

1.16

 Magazine

1.16

 Presents

1.10

 editor

1.08

 contributor

1.06

Magazine

1.03

Activations Density 0.330%

phrases related to editorial content and media personalities within a specific niche

mentions of various media outlets and publications

No Comments

No Known Activations