INDEX

Explanations

the word "discrimination"

oai_token-act-pair · gpt-3.5-turbo

words related to discrimination and inclusivity

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Siberian

-0.70

 Despair

-0.67

BOOK

-0.64

¥µ

-0.64

FORM

-0.63

Yug

-0.63

 menstrual

-0.61

LOAD

-0.60

 Sahara

-0.59

Downloadha

-0.59

POSITIVE LOGITS

ount

1.21

onduct

1.12

ussion

1.03

uity

1.00

retion

0.99

acies

0.99

ornia

0.96

ussions

0.94

acia

0.93

ayne

0.92

Activations Density 0.010%

the word "discrimination"

words related to discrimination and inclusivity

No Known Activations