INDEX

Explanations

specific strings or patterns that do not correspond to full sentences or meaningful phrases

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

soDeliveryDate

-0.66

etheless

-0.62

sonian

-0.59

VERS

-0.57

EMS

-0.57

MEN

-0.56

issance

-0.56

ANK

-0.55

emonium

-0.55

vironment

-0.55

POSITIVE LOGITS

jri

0.56

 scan

0.51

 trough

0.48

tein

0.47

href

0.45

 wheelchair

0.44

 cere

0.44

 slider

0.44

\)

0.44

cub

0.43

Activations Density 1.806%

specific strings or patterns that do not correspond to full sentences or meaningful phrases

No Comments

No Known Activations