INDEX

Explanations

references to Getty Images

oai_token-act-pair · gpt-3.5-turbo

references to Getty Images

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 bond

-0.74

 bonds

-0.72

 tongue

-0.71

 Zone

-0.69

 plat

-0.66

 ribbon

-0.65

 fare

-0.64

 zone

-0.64

 chapter

-0.63

 Deer

-0.63

POSITIVE LOGITS

Getty

3.79

 Getty

1.93

AFP

1.59

Reuters

1.56

Flickr

1.43

EPA

1.40

utterstock

1.37

Bloomberg

1.34

ulton

1.30

GET

1.30

Activations Density 0.018%

references to Getty Images

references to Getty Images

No Comments

No Known Activations