INDEX

Explanations

cryptocurrency-related terms and abbreviations

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

 Eisenhower

-0.95

 Scully

-0.84

 Foley

-0.83

 Faul

-0.81

 Curt

-0.74

 Fleming

-0.72

 Shepard

-0.71

 Wolver

-0.70

ttes

-0.69

 Wolverine

-0.68

POSITIVE LOGITS

BTC

1.66

Bitcoin

1.62

bitcoin

1.60

urrencies

1.57

rencies

1.56

coin

1.53

 cryptocurrencies

1.51

Coin

1.49

 Ethereum

1.48

 cryptocurrency

1.48

Activations Density 0.220%

cryptocurrency-related terms and abbreviations

No Comments

No Known Activations