INDEX

Explanations

mentions of the word "Lottery" specifically

oai_token-act-pair · gpt-3.5-turbo

mentions of lottery-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

iasm

-0.70

anwhile

-0.69

 streng

-0.64

Accessory

-0.64

 lockdown

-0.63

perty

-0.63

incinn

-0.62

izophren

-0.62

 rall

-0.62

PLIED

-0.61

POSITIVE LOGITS

tery

1.43

Lot

1.16

Lot

0.96

lot

0.89

bo

0.85

ter

0.77

oys

0.76

 Bagg

0.76

oday

0.72

aird

0.70

Activations Density 0.008%

mentions of the word "Lottery" specifically

mentions of lottery-related terms

No Comments

No Known Activations