INDEX

Explanations

specific years mentioned

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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 predec

-0.67

bom

-0.57

 disadvant

-0.56

 nearest

-0.55

 undermin

-0.55

edIn

-0.54

 Vaugh

-0.54

 fitt

-0.51

jri

-0.49

ogether

-0.49

POSITIVE LOGITS

 âĢº

0.51

 Updated

0.51

DragonMagazine

0.50

 partName

0.50

mega

0.50

 OnePlus

0.50

 Xiaomi

0.49

 COUNTY

0.49

photos

0.48

ISON

0.48

Activations Density 0.326%

specific years mentioned

references to specific dates and time periods

No Comments

No Known Activations