INDEX

Explanations

mentions of names or titles starting with "Mil" followed by a number

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Mil" or similar variations thereof

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 depreciation

-0.76

OPLE

-0.72

LY

-0.71

 compr

-0.71

ORTS

-0.69

 Sorceress

-0.66

BOOK

-0.65

Ħ¢

-0.65

 Atlantis

-0.64

IELD

-0.64

POSITIVE LOGITS

estones

1.37

estone

1.32

ksh

1.29

waukee

1.25

gram

1.16

isec

1.15

ieu

1.13

itant

1.08

itar

1.06

itary

1.03

Activations Density 0.029%

mentions of names or titles starting with "Mil" followed by a number

mentions of the name "Mil" or similar variations thereof

No Comments

No Known Activations