INDEX

Explanations

mentions of trends or comparisons related to significant changes or advancements

oai_token-act-pair · gpt-3.5-turbo

conditional phrases related to comparisons or changes in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Azerb

-0.73

ONSORED

-0.73

enegger

-0.70

 Niet

-0.70

ãĤ©

-0.67

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.66

Recomm

-0.66

ãĤ¡

-0.66

 arrang

-0.65

ãĥ¡

-0.65

POSITIVE LOGITS

uties

0.65

 converge

0.63

hooting

0.59

Â¶

0.59

arnaev

0.58

ucker

0.58

hots

0.56

 Released

0.55

Ã¶n

0.55

ensed

0.53

Activations Density 0.560%

mentions of trends or comparisons related to significant changes or advancements

conditional phrases related to comparisons or changes in data

No Comments

No Known Activations