INDEX

Explanations

phrases indicating significant monetary value or worth

oai_token-act-pair · gpt-3.5-turbo

phrases indicating monetary value or worth

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

Uri

-0.78

 Ribbon

-0.77

 Plain

-0.75

Ern

-0.71

 Belle

-0.71

Gaw

-0.69

 Aval

-0.68

 Apocalypse

-0.67

Kub

-0.67

 Rumble

-0.67

POSITIVE LOGITS

 worth

1.01

worth

0.89

folios

0.88

ensing

0.86

ume

0.82

iness

0.78

INGTON

0.77

umes

0.76

 cumulative

0.75

poons

0.74

Activations Density 0.010%

phrases indicating significant monetary value or worth

phrases indicating monetary value or worth

No Comments

No Known Activations