INDEX

Explanations

words related to a specific geographical location, "Utica."

oai_token-act-pair · gpt-3.5-turbo

references to the abbreviation "Ut" or related phrases

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

pmwiki

-0.76

 Carnival

-0.64

 thinner

-0.62

naire

-0.62

 Candy

-0.62

boards

-0.62

Magikarp

-0.61

anwhile

-0.61

overs

-0.61

backer

-0.60

POSITIVE LOGITS

ilitarian

1.32

tering

1.15

ted

1.10

rue

1.09

ility

1.09

ils

1.06

ting

1.01

ter

1.01

ilities

1.00

tle

0.98

Activations Density 0.024%

words related to a specific geographical location, "Utica."

references to the abbreviation "Ut" or related phrases

No Comments

No Known Activations