INDEX

Explanations

brand names or significant entities

oai_token-act-pair · gpt-3.5-turbo

terms indicating global rankings or prominence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

creen

-0.73

Downloadha

-0.72

 photoc

-0.68

ãĥ¼ãĥĨ

-0.68

anwhile

-0.67

isode

-0.63

NEC

-0.63

yout

-0.62

 polyg

-0.62

 interf

-0.61

POSITIVE LOGITS

¬

1.20

ħ

1.16

Ĵ

1.13

ı

1.09

¡

1.07

Ļ

1.03

į

1.01

ĵ

1.00

Ħ¢

1.00

ķ

1.00

Activations Density 0.209%

brand names or significant entities

terms indicating global rankings or prominence

No Comments

No Known Activations