INDEX

Explanations

proper nouns related to people named Wallace

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Wallace" and associated individuals

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lia

-0.76

mal

-0.76

milo

-0.76

ional

-0.75

uate

-0.74

amins

-0.73

ibal

-0.72

uncle

-0.71

mine

-0.70

unal

-0.70

POSITIVE LOGITS

 Wallace

1.11

mouth

0.79

 Strait

0.79

 Stevens

0.76

 Cros

0.74

 Walls

0.73

 Ellis

0.73

 Borders

0.73

 Williams

0.71

 Hampton

0.70

Activations Density 0.014%

proper nouns related to people named Wallace

mentions of the name "Wallace" and associated individuals

No Comments

No Known Activations