INDEX

Explanations

proper nouns related to a specific location, specifically, Washington

oai_token-act-pair · gpt-3.5-turbo

references to the location Washington

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gger

-0.77

 whilst

-0.74

 realise

-0.73

:-

-0.72

 realised

-0.72

Tes

-0.71

âĶĢâĶĢ

-0.71

 metre

-0.70

ĵ

-0.68

 util

-0.67

POSITIVE LOGITS

 Washington

3.55

Washington

3.27

WASHINGTON

1.77

ASHINGTON

1.73

ashington

1.66

 Wash

1.65

 Seattle

1.63

 Ottawa

1.56

 Arlington

1.55

 Spokane

1.54

Activations Density 0.023%

proper nouns related to a specific location, specifically, Washington

references to the location Washington

No Comments

No Known Activations