INDEX

Explanations

mentions of royalty, specifically queens

oai_token-act-pair · gpt-3.5-turbo

mentions of royalty, specifically various queens

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

nir

-0.72

ramid

-0.71

odcast

-0.66

quickShipAvailable

-0.66

oday

-0.65

herer

-0.64

aneous

-0.64

aneously

-0.64

 Canaver

-0.63

onto

-0.63

POSITIVE LOGITS

 Elizabeth

1.24

 Anne

1.17

 Victoria

1.07

 Alexandra

1.06

 Mary

1.02

 Esther

0.98

 Mother

0.98

Bee

0.95

 Margaret

0.94

stown

0.89

Activations Density 0.023%

mentions of royalty, specifically queens

mentions of royalty, specifically various queens

No Comments

No Known Activations