INDEX

Explanations

mentions or references to lotteries

oai_token-act-pair · gpt-3.5-turbo

references to lottery-related terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

contained

-0.70

english

-0.69

ths

-0.68

cam

-0.67

stood

-0.66

icas

-0.66

Interstitial

-0.65

sis

-0.64

 Calm

-0.62

Cam

-0.62

POSITIVE LOGITS

 lottery

1.20

tery

0.89

eers

0.85

stakes

0.80

Lot

0.78

 Sabha

0.74

 ticket

0.71

 tickets

0.70

 absor

0.68

 vouchers

0.67

Activations Density 0.006%

mentions or references to lotteries

references to lottery-related terms and concepts

No Comments

No Known Activations