INDEX

Explanations

locations, political terms, and organizations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 UFOs

-0.74

xual

-0.70

Terror

-0.70

ipedia

-0.68

 whilst

-0.66

 impunity

-0.63

 leaks

-0.62

 youtube

-0.62

 torture

-0.61

 inventions

-0.61

POSITIVE LOGITS

 northeastern

0.83

 southwestern

0.81

 southwest

0.77

 northwestern

0.75

 Northeast

0.75

 northeast

0.73

 northwest

0.73

 Southwest

0.70

 Prairie

0.70

 southeast

0.69

Activations Density 0.706%

locations, political terms, and organizations

No Comments

No Known Activations