INDEX

Explanations

locations or headquarters of organizations or companies

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate location or origin of entities

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

 hurled

-0.78

umatic

-0.75

fters

-0.74

 wielded

-0.73

 accustomed

-0.72

 tempted

-0.70

vous

-0.69

fter

-0.69

xual

-0.69

 consumed

-0.69

POSITIVE LOGITS

 northeast

0.99

 conjunction

0.99

 northwest

0.98

 northeastern

0.97

 Southeast

0.96

 Vienna

0.94

 northwestern

0.93

 Bangalore

0.92

 Alexandria

0.92

 southwestern

0.91

Activations Density 0.118%

locations or headquarters of organizations or companies

phrases that indicate location or origin of entities

No Comments

No Known Activations