INDEX

Explanations

references to the philanthropic activities and associations of Bill Gates

oai_token-act-pair · gpt-3.5-turbo

mentions of Bill Gates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ccording

-0.73

»Ĵ

-0.73

hovah

-0.70

yrinth

-0.66

foundland

-0.65

 recourse

-0.65

 forc

-0.62

RANT

-0.62

pmwiki

-0.61

į

-0.61

POSITIVE LOGITS

worms

0.98

 Gates

0.90

zag

0.89

boro

0.85

pring

0.83

pin

0.79

borough

0.79

ilon

0.78

ocrates

0.78

mos

0.76

Activations Density 0.017%

references to the philanthropic activities and associations of Bill Gates

mentions of Bill Gates

No Comments

No Known Activations