INDEX

Explanations

Twitter handles

oai_token-act-pair · gpt-3.5-turbo

mentions of social media handles or usernames

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

senal

-0.84

 pneum

-0.70

 reconc

-0.67

chwitz

-0.67

 conversions

-0.66

 defic

-0.66

Vie

-0.65

 Malk

-0.64

ļé

-0.63

 Zamb

-0.63

POSITIVE LOGITS

#$

1.30

@@@@@@@@

1.01

realDonaldTrump

1.00

"@

0.94

cade

0.81

gmail

0.78

wik

0.74

LINE

0.74

GOP

0.73

Activations Density 0.013%

Twitter handles

mentions of social media handles or usernames

No Comments

No Known Activations