INDEX

Explanations

words related to regulations and laws

oai_token-act-pair · gpt-3.5-turbo

direct speech or quotations

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

 Vaugh

-0.45

 helicop

-0.43

aturdays

-0.41

 Seym

-0.41

emale

-0.40

enegger

-0.39

ä»£

-0.38

ãĥĩãĤ£

-0.37

sic

-0.37

farious

-0.37

POSITIVE LOGITS

Â¶

0.35

 Rohingya

0.33

 OnePlus

0.32

Merit

0.32

 âĢº

0.31

 Abandon

0.31

Mos

0.31

 largeDownload

0.31

 Shin

0.30

Ars

0.30

Activations Density 5.434%

words related to regulations and laws

direct speech or quotations

No Comments

No Known Activations