INDEX

Explanations

proper nouns related to cities

oai_token-act-pair · gpt-3.5-turbo

mentions of major cities, particularly Berlin and Istanbul

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

venge

-0.76

Leod

-0.73

vana

-0.73

istration

-0.71

redo

-0.70

++++

-0.68

estern

-0.67

aved

-0.66

Chuck

-0.66

pring

-0.66

POSITIVE LOGITS

 Airport

0.95

 airport

0.93

 City

0.92

 Municip

0.92

 metropolitan

0.92

 Hilton

0.91

 suburb

0.91

 harbor

0.88

 skyline

0.87

 city

0.87

Activations Density 0.076%

proper nouns related to cities

mentions of major cities, particularly Berlin and Istanbul

No Comments

No Known Activations