INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "In" followed by context-related phrases or statements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 ..."

-0.72

etc

-0.68

 âĢ¦"

-0.66

 buds

-0.63

fab

-0.63

åĤ

-0.62

 darn

-0.62

 nipples

-0.62

 chicks

-0.62

 ðŁĻĤ

-0.62

POSITIVE LOGITS

resa

1.38

odore

1.16

ogether

0.98

alyst

0.95

romeda

0.95

ventory

0.94

ccording

0.92

wards

0.90

xiety

0.90

nesty

0.88

Activations Density 0.519%

proper nouns

occurrences of the word "In" followed by context-related phrases or statements

No Comments

No Known Activations