INDEX

Explanations

mentions of the name "Sig" at varying levels of relevance and misspellings in text

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Sig" or its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

tical

-0.78

sers

-0.70

tics

-0.68

ģĸ

-0.68

 Remastered

-0.67

icative

-0.67

omorphic

-0.66

ãĥ¤

-0.66

suits

-0.65

 Shutterstock

-0.63

POSITIVE LOGITS

undo

1.07

urd

0.87

enda

0.86

reen

0.85

ifts

0.85

uel

0.84

ata

0.78

wered

0.78

ldom

0.77

esthesia

0.77

Activations Density 0.048%

mentions of the name "Sig" at varying levels of relevance and misspellings in text

mentions of the term "Sig" or its variations in context

No Comments

No Known Activations