INDEX

Explanations

mentions of "Greco-Roman" culture and related terms

oai_token-act-pair · gpt-3.5-turbo

references to corporate entities or businesses

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

 GOODMAN

-0.77

 Subjects

-0.64

acious

-0.63

 Hungarian

-0.63

 Skydragon

-0.62

ulia

-0.62

 Ninth

-0.61

Subject

-0.61

lihood

-0.60

 subjects

-0.60

POSITIVE LOGITS

xon

1.35

ffee

1.31

oldown

0.99

cephal

0.98

ff

0.97

ffe

0.97

asters

0.95

pper

0.95

zzi

0.95

operation

0.95

Activations Density 0.025%

mentions of "Greco-Roman" culture and related terms

references to corporate entities or businesses

No Comments

No Known Activations