INDEX

Explanations

the word "Marco"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Marco."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

shed

-0.73

Bow

-0.70

reth

-0.64

 workplaces

-0.64

 occup

-0.63

[&

-0.63

olson

-0.62

OU

-0.62

HQ

-0.61

hod

-0.61

POSITIVE LOGITS

 Marco

3.61

Marco

3.08

 Rubio

2.00

Jeb

1.54

 Roberto

1.33

 Giovanni

1.30

Cruz

1.28

 Rafael

1.26

 Cruz

1.26

 Lindsey

1.25

Activations Density 0.008%

the word "Marco"

mentions of the name "Marco."

No Comments

No Known Activations