INDEX

Explanations

Twitter usernames

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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Vale

-0.75

 exorc

-0.72

 Macedonia

-0.69

 Somers

-0.68

emonium

-0.66

 Presents

-0.65

 Nirvana

-0.63

 Reborn

-0.62

 collateral

-0.62

 seminal

-0.62

POSITIVE LOGITS

#$

1.25

realDonaldTrump

1.18

gmail

0.93

wik

0.89

lis

0.87

groups

0.82

gs

0.80

yss

0.77

Home

0.77

wcsstore

0.75

Activations Density 0.017%

Twitter usernames

mentions of social media handles or usernames

No Comments

No Known Activations