INDEX

Explanations

references to historical figures and events related to business

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 instance

-0.36

vac

-0.35

 חיצוניים

-0.34

 corriendo

-0.34

Vac

-0.32

email

-0.32

 Fernandez

-0.32

 مرئيه

-0.32

 dAtA

-0.31

epar

-0.31

POSITIVE LOGITS

 diversify

0.82

 diversification

0.81

 diversified

0.79

 diversi

0.76

Diver

0.63

 Diver

0.56

 specialization

0.54

 specialising

0.53

rrggbb

0.52

 '\\;'

0.52

Activations Density 0.326%

references to historical figures and events related to business

No Comments

No Known Activations