INDEX

Explanations

references to different locations and changes in residence

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

phrases related to movement from one place to another

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 staples

-0.78

immers

-0.76

loads

-0.76

ulner

-0.74

uggets

-0.73

Tokens

-0.72

 projectiles

-0.71

ensibly

-0.70

apses

-0.70

umes

-0.69

POSITIVE LOGITS

 country

1.73

 province

1.66

 locality

1.65

 region

1.56

 jurisdiction

1.55

 municipality

1.50

 town

1.47

 city

1.44

 suburb

1.42

 borough

1.42

Activations Density 0.277%

references to different locations and changes in residence

phrases related to movement from one place to another

No Comments

No Known Activations