INDEX

Explanations

phrases including the abbreviation "AN" followed by numbers, possibly related to technical terms or codes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "AN" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cind

-0.71

 Seym

-0.68

ments

-0.68

ourses

-0.65

ensional

-0.64

weed

-0.64

 Giuliani

-0.64

downs

-0.63

ï¸ı

-0.63

 guiIcon

-0.62

POSITIVE LOGITS

alyst

1.06

onymous

1.01

thood

0.99

ning

0.95

xiety

0.93

nex

0.93

OVA

0.92

ARCH

0.91

igans

0.91

omal

0.89

Activations Density 0.022%

phrases including the abbreviation "AN" followed by numbers, possibly related to technical terms or codes

occurrences of the abbreviation "AN" in various contexts

No Comments

No Known Activations