INDEX

Explanations

credit-related terms, especially related to credit cards

oai_token-act-pair · gpt-3.5-turbo

references to credit cards and related financial terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Bei

-0.79

gha

-0.73

hm

-0.71

tering

-0.70

zel

-0.70

cham

-0.66

theless

-0.65

Kus

-0.65

++++++++

-0.65

 Siem

-0.63

POSITIVE LOGITS

 card

1.25

card

1.17

worthiness

1.13

 CARD

1.13

 cards

1.09

cards

1.09

 Cards

0.97

Card

0.97

 Card

0.88

worthy

0.87

Activations Density 0.025%

credit-related terms, especially related to credit cards

references to credit cards and related financial terms

No Comments

No Known Activations