INDEX

Explanations

phrases related to comparisons of quantity or quality

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significant modifications or changes

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

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

 Solitaire

-0.87

 Borders

-0.85

 Compass

-0.76

SOL

-0.72

 Polo

-0.71

 Stellar

-0.71

 Satellite

-0.71

 Colors

-0.70

 boundaries

-0.70

 Hole

-0.69

POSITIVE LOGITS

needed

1.45

awaited

1.29

respected

1.27

anticipated

1.24

earned

1.20

valued

1.20

advert

1.19

known

1.12

powerful

1.11

des

1.08

Activations Density 0.038%

phrases related to comparisons of quantity or quality

phrases indicating significant modifications or changes

No Comments

No Known Activations