INDEX

Explanations

mentions of specific online publications, such as Slate and Wired

oai_token-act-pair · gpt-3.5-turbo

mentions of specific media outlets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 captcha

-0.73

 awoken

-0.69

unts

-0.66

 sovere

-0.65

rul

-0.64

araoh

-0.63

 bonding

-0.61

installed

-0.61

henko

-0.60

cles

-0.60

POSITIVE LOGITS

 Magazine

1.33

Magazine

1.29

 magazine

1.19

 Weekly

1.04

News

0.96

 Publishing

0.94

 Newsp

0.94

 Editors

0.93

Leaks

0.93

 Editorial

0.93

Activations Density 0.112%

mentions of specific online publications, such as Slate and Wired

mentions of specific media outlets

No Comments

No Known Activations