INDEX

Explanations

elements consistent with scientific or technical notation and terminology

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

verwijspagina

-0.61

 kasarigan

-0.49

Datuak

-0.48

出版年

-0.47

endregion

-0.46

Rhestr

-0.44

ollectionView

-0.42

 esat

-0.41

Demografie

-0.40

sizeCache

-0.40

POSITIVE LOGITS

/*

0.43

يكب

0.43

principalTable

0.42

=$?

0.42

fran

0.42

 manifeste

0.39

stoff

0.39

gub

0.38

gawai

0.38

frank

0.38

Activations Density 1.026%

elements consistent with scientific or technical notation and terminology

No Comments

No Known Activations