INDEX

Explanations

phrases indicating activities or actions performed by individuals on social media platforms

oai_token-act-pair · gpt-3.5-turbo

expressions indicating an action of taking to social media or public platforms

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

<-

-0.62

frames

-0.62

 Machina

-0.61

 Mage

-0.59

Gap

-0.59

ONSORED

-0.58

 cheated

-0.57

 hypoc

-0.57

 discriminated

-0.56

holders

-0.55

POSITIVE LOGITS

pless

0.86

ãĥīãĥ©

0.75

pload

0.70

 form

0.67

wing

0.66

psy

0.61

onement

0.61

rolet

0.61

 externalToEVAOnly

0.61

aptic

0.60

Activations Density 0.045%

phrases indicating activities or actions performed by individuals on social media platforms

expressions indicating an action of taking to social media or public platforms

No Comments

No Known Activations