INDEX

Explanations

words related to buying and selling goods or services

oai_token-act-pair · gpt-3.5-turbo

phrases related to items or products being for sale

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

 Stro

-0.76

ference

-0.75

aired

-0.71

 Ange

-0.67

 Daylight

-0.64

 Miko

-0.64

kiss

-0.64

raction

-0.63

sis

-0.62

laus

-0.61

POSITIVE LOGITS

 prices

1.17

 price

1.05

 discounts

1.04

 auctions

1.02

 sellers

0.99

 listings

0.98

Price

0.95

 priced

0.93

stores

0.92

 paperback

0.91

Activations Density 0.113%

words related to buying and selling goods or services

phrases related to items or products being for sale

No Comments

No Known Activations