INDEX

Explanations

locations or proper nouns related to cities or towns

oai_token-act-pair · gpt-3.5-turbo

mentions of geographic locations, particularly cities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

aith

-0.78

Gra

-0.72

oud

-0.70

bip

-0.69

Bow

-0.69

Dob

-0.69

od

-0.68

Cy

-0.67

Kay

-0.66

ae

-0.66

POSITIVE LOGITS

 Shanghai

3.16

ghai

1.48

 Valencia

1.35

 Deng

1.28

 Disneyland

1.13

Qin

1.07

 yuan

1.05

 Cinderella

1.05

 Mandarin

1.03

 Guang

0.97

Activations Density 0.025%

locations or proper nouns related to cities or towns

mentions of geographic locations, particularly cities

No Comments

No Known Activations