INDEX

Explanations

phrases related to ensuring something is managed or executed in a specified manner

oai_token-act-pair · gpt-3.5-turbo

phrases focused on ensuring or guaranteeing outcomes or conditions

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

 Hancock

-0.86

BuyableInstoreAndOnline

-0.85

quickShipAvailable

-0.77

EStreamFrame

-0.71

 Twain

-0.71

 Shutterstock

-0.71

################

-0.68

ELD

-0.66

 Sheikh

-0.65

 Cosponsors

-0.64

POSITIVE LOGITS

 survives

0.76

 identity

0.69

 safe

0.68

 uninterrupted

0.67

 perman

0.66

 footing

0.66

burse

0.63

ancial

0.62

 whereabouts

0.61

 protects

0.61

Activations Density 0.175%

phrases related to ensuring something is managed or executed in a specified manner

phrases focused on ensuring or guaranteeing outcomes or conditions

No Comments

No Known Activations