INDEX

Explanations

words or phrases related to the name "Jakak"

oai_token-act-pair · gpt-3.5-turbo

the presence of specific names or terms associated with Japanese culture or media

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

Ö¼

-0.71

ãĤ¡

-0.70

 pint

-0.66

 alcohol

-0.64

ORPG

-0.62

drops

-0.61

 Fenrir

-0.61

 balloons

-0.61

 dividend

-0.61

 Collider

-0.60

POSITIVE LOGITS

arak

1.21

unin

1.19

ota

1.10

umar

1.07

ansas

1.02

ihara

1.00

sha

0.96

rish

0.96

ushi

0.95

istani

0.95

Activations Density 0.023%

words or phrases related to the name "Jakak"

the presence of specific names or terms associated with Japanese culture or media

No Comments

No Known Activations