INDEX

Explanations

locations, specifically cities and regions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

VALUE

-0.79

thood

-0.73

renheit

-0.69

 magnification

-0.68

onym

-0.62

anamo

-0.62

LOAD

-0.61

hol

-0.60

@@@@@@@@

-0.60

vana

-0.60

POSITIVE LOGITS

shire

1.33

 Borough

0.97

 County

0.89

 Heights

0.82

 City

0.81

 Province

0.81

 Bulldogs

0.79

ois

0.78

Zoo

0.77

 Avenue

0.76

Activations Density 0.172%

locations, specifically cities and regions

place names or locations

No Comments

No Known Activations