INDEX

Explanations

references to specific newspapers or media outlets

oai_token-act-pair · gpt-3.5-turbo

references to news 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sed

-0.80

chwitz

-0.75

liam

-0.72

etime

-0.68

depend

-0.67

adow

-0.66

cles

-0.65

milo

-0.64

ackle

-0.63

 vocals

-0.63

POSITIVE LOGITS

 Herald

1.20

 Tribune

1.18

 Chronicle

1.11

 Observer

1.03

 Newspaper

1.00

 Newsp

0.97

 Inqu

0.94

 Editorial

0.93

 Wire

0.92

 Dispatch

0.91

Activations Density 0.138%

references to specific newspapers or media outlets

references to news outlets and publications

No Comments

No Known Activations