INDEX

Explanations

references or mentions of the word "Ad"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Ad."

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

ĸļ

-0.79

GoldMagikarp

-0.71

Ń·

-0.70

 trout

-0.68

Jr

-0.68

 biomass

-0.67

 Stronghold

-0.66

 Weir

-0.65

 pinch

-0.63

 Kubrick

-0.62

POSITIVE LOGITS

vertis

1.37

elaide

1.30

vertising

1.24

vantage

1.23

mittedly

1.19

vertisements

1.15

vance

1.12

ventures

1.12

idas

1.10

roit

1.08

Activations Density 0.025%

references or mentions of the word "Ad"

mentions of the word "Ad."

No Comments

No Known Activations