INDEX

Explanations

phrases related to statements or declarations

oai_token-act-pair · gpt-3.5-turbo

the character "Ļ"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

undown

-0.67

CLR

-0.62

 Palestin

-0.61

 charisma

-0.60

 Kindle

-0.60

 Morse

-0.59

 paperback

-0.59

 multiplication

-0.59

Rez

-0.59

 unbeliev

-0.58

POSITIVE LOGITS

ï¸ı

0.96

together

0.92

agree

0.91

selves

0.89

yg

0.85

east

0.83

Â·Â·

0.81

sure

0.81

mand

0.80

else

0.77

Activations Density 0.131%

phrases related to statements or declarations

the character "Ļ"

No Comments

No Known Activations