INDEX

Explanations

references to locations or entities with 'White' in their name

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "White" in relation to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

REM

-0.83

cffffcc

-0.79

ANS

-0.78

Downloadha

-0.75

ITAL

-0.74

udeau

-0.73

olls

-0.71

vati

-0.69

ript

-0.68

APH

-0.67

POSITIVE LOGITS

Sox

1.14

caps

1.13

horse

1.10

hall

1.10

 supremacist

1.05

 supremacists

1.02

beard

1.01

house

0.97

bread

0.95

 Sands

0.93

Activations Density 0.021%

references to locations or entities with 'White' in their name

mentions of the word "White" in relation to various contexts

No Comments

No Known Activations