INDEX

Explanations

keywords related to credit and debit card transactions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

gha

-0.73

zel

-0.72

Bei

-0.68

xy

-0.68

hm

-0.68

,,,,

-0.67

Wem

-0.67

++++++++

-0.66

tering

-0.66

 Siem

-0.65

POSITIVE LOGITS

 card

1.35

card

1.27

 cards

1.22

 CARD

1.18

cards

1.17

worthiness

1.15

Card

1.08

 Cards

1.07

worthy

1.00

 Card

0.94

Activations Density 0.025%

keywords related to credit and debit card transactions

No Comments

No Known Activations