INDEX

Explanations

the word "editor"

oai_token-act-pair · gpt-3.5-turbo

mentions of editors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

achi

-0.80

rises

-0.75

pered

-0.74

ulus

-0.74

ramid

-0.73

wn

-0.71

alsa

-0.69

ptoms

-0.67

si

-0.67

ffff

-0.66

POSITIVE LOGITS

editor

1.14

 editor

1.09

 Editor

0.87

ials

0.83

ially

0.81

 Editors

0.76

 editing

0.75

 editors

0.74

 drawer

0.74

 pane

0.73

Activations Density 0.011%

the word "editor"

mentions of editors

No Comments

No Known Activations