INDEX

Explanations

references to mold in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to mold and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

WTO

-0.70

ZE

-0.70

ights

-0.67

 Ended

-0.66

atre

-0.66

 Hath

-0.65

 FANTASY

-0.64

ods

-0.64

ãĤ³

-0.64

 Loan

-0.64

POSITIVE LOGITS

ering

1.21

ered

1.03

erer

1.01

ovan

0.99

erers

0.99

ing

0.97

eer

0.96

ery

0.86

smanship

0.85

eers

0.85

Activations Density 0.074%

references to mold in various contexts

references to mold and its implications

No Comments

No Known Activations