INDEX

Explanations

proper nouns and specific terms

oai_token-act-pair · gpt-3.5-turbo

phrases related to interactions and processes involving artificial intelligence and technology

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

 Schiff

-0.71

 Tiff

-0.68

JPM

-0.61

 Cheng

-0.60

ÄŁ

-0.60

 Lawn

-0.58

 Excel

-0.57

 Merkel

-0.56

 Zhao

-0.56

 Xander

-0.56

POSITIVE LOGITS

 thereof

1.96

 thereto

1.60

 therein

1.51

 accordingly

1.30

 thereafter

0.96

them

0.96

 consequ

0.89

 ensuing

0.89

sequently

0.83

 resultant

0.83

Activations Density 0.806%

proper nouns and specific terms

phrases related to interactions and processes involving artificial intelligence and technology

No Comments

No Known Activations