INDEX

Explanations

phrases related to legal or formal statements

oai_token-act-pair · gpt-3.5-turbo

references and citations in text

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

terday

-0.75

Suddenly

-0.74

chant

-0.70

 Suddenly

-0.68

Enlarge

-0.68

dayName

-0.62

ellation

-0.61

 tion

-0.60

 divest

-0.60

ggle

-0.60

POSITIVE LOGITS

 disclaim

0.96

 disclaimer

0.94

 ital

0.93

 spoilers

0.92

 copyrighted

0.89

 trademarks

0.88

 excludes

0.87

 formatting

0.85

 PLEASE

0.84

 MUST

0.84

Activations Density 0.874%

phrases related to legal or formal statements

references and citations in text

No Comments

No Known Activations