INDEX

Explanations

phrases related to possession or ownership

oai_token-act-pair · gpt-3.5-turbo

terms that indicate legal or formal language, particularly regarding ownership and obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

paren

-0.74

cho

-0.69

ku

-0.60

zers

-0.60

asio

-0.60

rm

-0.59

ducers

-0.59

mber

-0.59

 Michel

-0.59

UE

-0.59

POSITIVE LOGITS

atsu

0.83

hower

0.82

selves

0.81

rack

0.79

é¾įåĸļå£«

0.76

 therein

0.75

00200000

0.71

orld

0.71

soever

0.71

ufact

0.71

Activations Density 0.078%

phrases related to possession or ownership

terms that indicate legal or formal language, particularly regarding ownership and obligations

No Comments

No Known Activations