INDEX

Explanations

credit card-related terms and transactions

oai_token-act-pair · gpt-3.5-turbo

terms related to credit cards and their transactions

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

é¾

-0.84

 Atmosp

-0.75

velength

-0.70

Hoo

-0.70

Ago

-0.67

ixels

-0.67

 fract

-0.66

ç«

-0.66

GMT

-0.65

Ó

-0.64

POSITIVE LOGITS

inals

1.10

 issuer

0.99

 debit

0.92

holder

0.91

holders

0.83

 credentials

0.83

 swipe

0.81

 purchases

0.80

iovascular

0.80

card

0.79

Activations Density 0.027%

credit card-related terms and transactions

terms related to credit cards and their transactions

No Comments

No Known Activations