INDEX

Explanations

pronouns or nouns denoting individuals distancing themselves from others or groups

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 understatement

-0.62

WORK

-0.62

 roundup

-0.61

amental

-0.57

heny

-0.56

 Stephenson

-0.56

 visitation

-0.56

 nightmares

-0.55

 Fulton

-0.55

 eyebrow

-0.54

POSITIVE LOGITS

selves

0.88

é¾įåĸļå£«

0.81

 creatively

0.79

ternally

0.77

DragonMagazine

0.77

 territ

0.74

 tremend

0.74

é¾įå¥ĳå£«

0.71

 withd

0.71

éĸ

0.70

Activations Density 0.043%

pronouns or nouns denoting individuals distancing themselves from others or groups

No Comments

No Known Activations