INDEX

Explanations

phrases related to policies, decisions, or positions

oai_token-act-pair · gpt-3.5-turbo

the presence of specific punctuation or formatting markers

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

ģĸ

-0.74

 diplom

-0.71

adm

-0.69

 differe

-0.69

é¾įå¥ĳå£«

-0.68

æ©

-0.68

 Aval

-0.66

 Slov

-0.66

 compe

-0.65

 phyl

-0.65

POSITIVE LOGITS

redict

1.30

aired

1.28

ossession

1.27

ossible

1.24

ulse

1.18

ardon

1.17

uzzle

1.17

ierce

1.16

odcast

1.16

uls

1.16

Activations Density 0.034%

phrases related to policies, decisions, or positions

the presence of specific punctuation or formatting markers

No Comments

No Known Activations