INDEX

Explanations

phrases related to edited or amended content

oai_token-act-pair · gpt-3.5-turbo

bullet points or list items

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

omorphic

-0.81

ushi

-0.76

ritic

-0.72

 wagon

-0.72

 grain

-0.71

brance

-0.71

etheless

-0.71

ourced

-0.69

quist

-0.69

 bending

-0.68

POSITIVE LOGITS

âĢ¢âĢ¢

1.44

âĢ¢âĢ¢âĢ¢âĢ¢

1.28

âĢ¢

1.00

ï¸ı

0.92

âĸł

0.87

---------

0.83

âĻ¦

0.83

ï¸

0.82

 Includes

0.79

----------------------------------------------------------------

0.78

Activations Density 0.009%

phrases related to edited or amended content

bullet points or list items

No Comments

No Known Activations