INDEX

Explanations

editorial notes within a document

oai_token-act-pair · gpt-3.5-turbo

references to editorial notes or comments

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

rises

-0.75

pered

-0.73

avid

-0.68

ffff

-0.68

crow

-0.66

 Estonia

-0.66

mallow

-0.65

bands

-0.64

 Vulcan

-0.64

ought

-0.64

POSITIVE LOGITS

Editor

0.95

 Editor

0.87

 Editors

0.86

editor

0.81

 Clicker

0.81

ially

0.80

ial

0.73

 Editorial

0.73

 Reader

0.72

 editor

0.71

Activations Density 0.009%

editorial notes within a document

references to editorial notes or comments

No Comments

No Known Activations