INDEX

Explanations

information about individuals related to editorial roles and social media, specifically Twitter

oai_token-act-pair · gpt-3.5-turbo

mentions of social media interactions and author attributions

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

•twitter related features

No Comments

Negative Logits

haar

-0.73

 QuÃ©

-0.65

aceae

-0.63

 guiActiveUnfocused

-0.61

 blush

-0.59

Enlarge

-0.59

 Bind

-0.58

 Finder

-0.58

othal

-0.58

rue

-0.58

POSITIVE LOGITS

Subscribe

0.64

 Viper

0.63

 TAMADRA

0.62

 Virtue

0.60

 Pact

0.57

iframe

0.54

 chats

0.53

Vs

0.53

channel

0.53

 Podcast

0.52

Activations Density 0.163%

information about individuals related to editorial roles and social media, specifically Twitter

mentions of social media interactions and author attributions

No Comments

No Known Activations