INDEX

Explanations

Twitter handles beginning with '@'

oai_token-act-pair · gpt-3.5-turbo

mentions of social media handles or tags

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emonium

-0.73

 pneum

-0.73

 circulation

-0.68

 rebell

-0.64

 liner

-0.64

 Primordial

-0.64

monary

-0.64

 Dise

-0.63

 contracting

-0.63

 Xiang

-0.62

POSITIVE LOGITS

#$

1.48

@@@@@@@@

1.14

realDonaldTrump

1.09

Home

0.94

aic

0.92

gmail

0.89

home

0.83

TE

0.80

las

0.79

GS

0.78

Activations Density 0.013%

Twitter handles beginning with '@'

mentions of social media handles or tags

No Comments

No Known Activations