INDEX

Explanations

phrases where the words "you guys" are mentioned

oai_token-act-pair · gpt-3.5-turbo

references to a specific group of people or audience, often using the term "you guys."

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

BuyableInstoreAndOnline

-0.67

Weather

-0.67

Lv

-0.66

FN

-0.65

HUD

-0.65

Var

-0.63

 Sinn

-0.62

WOR

-0.61

CLR

-0.60

Attempt

-0.59

POSITIVE LOGITS

 yourselves

0.95

pez

0.83

cale

0.79

nesday

0.75

edient

0.73

owe

0.72

selves

0.71

 wanna

0.69

 pardon

0.68

ortium

0.67

Activations Density 0.078%

phrases where the words "you guys" are mentioned

references to a specific group of people or audience, often using the term "you guys."

No Comments

No Known Activations