INDEX

Explanations

the word "Duncan" followed by a range of numbers

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Duncan."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Magikarp

-0.78

ī

-0.72

xual

-0.71

othal

-0.71

orical

-0.70

Ĳ

-0.70

hovah

-0.69

heny

-0.69

¥µ

-0.69

ĻĤ

-0.68

POSITIVE LOGITS

 Duncan

0.96

ienne

0.86

Leaks

0.83

aldo

0.78

geon

0.78

 Hunter

0.76

IELD

0.76

endi

0.75

 Keith

0.74

neau

0.74

Activations Density 0.029%

the word "Duncan" followed by a range of numbers

mentions of the name "Duncan."

No Comments

No Known Activations