INDEX

Explanations

specific references to international geopolitical relations

oai_token-act-pair · gpt-3.5-turbo

references to nations and international relations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

urations

-0.82

Enough

-0.75

veyard

-0.73

Throw

-0.70

Station

-0.70

Bay

-0.69

Female

-0.66

iple

-0.65

Accessory

-0.64

Hand

-0.64

POSITIVE LOGITS

 nations

1.15

wide

0.91

 countries

0.87

chool

0.87

 Countries

0.80

wana

0.80

 Instruments

0.78

icz

0.77

 worldwide

0.73

 Nations

0.73

Activations Density 0.008%

specific references to international geopolitical relations

references to nations and international relations

No Comments

No Known Activations