INDEX

Explanations

mentions of awards and honors received by individuals

oai_token-act-pair · gpt-3.5-turbo

references to various prestigious awards and nominations within the entertainment industry

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abal

-0.86

dayName

-0.84

nel

-0.83

forums

-0.75

ontent

-0.73

cdn

-0.73

eneg

-0.72

eteria

-0.72

soDeliveryDate

-0.72

mop

-0.72

POSITIVE LOGITS

 prestigious

1.20

 honors

1.10

 Prize

1.00

 awards

1.00

 award

0.97

 accol

0.97

 prizes

0.96

 Award

0.96

inguished

0.95

 Awards

0.91

Activations Density 0.437%

mentions of awards and honors received by individuals

references to various prestigious awards and nominations within the entertainment industry

No Comments

No Known Activations