INDEX

Explanations

academic positions and affiliations, particularly with universities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating academic positions and affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Console

-0.82

execute

-0.75

sticks

-0.74

 wagon

-0.73

repeat

-0.72

 glide

-0.71

boats

-0.71

filter

-0.71

Owner

-0.70

 horizont

-0.69

POSITIVE LOGITS

 University

1.35

 UCLA

1.30

 universities

1.30

 Harvard

1.29

 university

1.28

NYU

1.28

 Cornell

1.24

 Georgetown

1.23

 Rutgers

1.20

 Stanford

1.20

Activations Density 0.103%

academic positions and affiliations, particularly with universities

phrases indicating academic positions and affiliations

No Comments

No Known Activations