INDEX

Explanations

locations in the United States

oai_token-act-pair · gpt-3.5-turbo

place names or locations

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

 Reincarn

-0.79

thood

-0.71

 favourable

-0.69

 apologise

-0.69

 tyre

-0.66

sbm

-0.61

Rs

-0.60

 stret

-0.60

 chromosomes

-0.59

 Patron

-0.59

POSITIVE LOGITS

adelphia

1.09

TX

1.01

shire

1.00

 Township

1.00

 Heights

0.99

ville

0.99

town

0.94

 suburb

0.93

burg

0.92

 Janeiro

0.91

Activations Density 0.361%

locations in the United States

place names or locations

No Comments

No Known Activations