INDEX

Explanations

terms related to financial transactions, specifically focusing on debit and prepaid cards

oai_token-act-pair · gpt-3.5-turbo

references to various forms of debit and prepaid payment methods

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

xual

-0.89

itals

-0.78

ppa

-0.75

ynt

-0.74

quartered

-0.73

ologies

-0.72

Ń·

-0.72

unin

-0.71

alus

-0.71

isted

-0.71

POSITIVE LOGITS

 debit

0.99

 card

0.87

card

0.84

 CARD

0.81

BLIC

0.79

lace

0.78

itures

0.78

PIN

0.78

iture

0.74

cart

0.74

Activations Density 0.045%

terms related to financial transactions, specifically focusing on debit and prepaid cards

references to various forms of debit and prepaid payment methods

No Comments

No Known Activations