INDEX

Explanations

dates and specific time frames mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to specific dates and time periods

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

bom

-0.52

 predec

-0.52

 fitt

-0.50

 Vaugh

-0.48

 corrid

-0.48

 referen

-0.44

 redes

-0.44

 Niet

-0.43

 hemor

-0.43

accompan

-0.43

POSITIVE LOGITS

 âĢº

0.48

weed

0.46

bitcoin

0.46

bush

0.45

justice

0.44

 Xiaomi

0.44

CLAIM

0.44

 Updated

0.44

 OnePlus

0.43

Activations Density 0.407%

dates and specific time frames mentioned in the text

references to specific dates and time periods

No Comments

No Known Activations