INDEX

Explanations

technical terms and phrases related to scientific measurements and analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 GenerationType

-0.58

Carcinogenicity

-0.58

 للاسماء

-0.52

 nhưng

-0.52

 ejecutivo

-0.51

ContentAsync

-0.51

HasAnnotation

-0.50

ItemBackground

-0.50

CloseOperation

-0.50

ortunadamente

-0.50

POSITIVE LOGITS

pushFollow

0.43

skjaer

0.39

قایناقلار

0.33

 المل

0.33

Mos

0.32

MigrationBuilder

0.31

 ivelany

0.30

Oss

0.30

 AttributeSet

0.30

weiser

0.30

Activations Density 1.752%

technical terms and phrases related to scientific measurements and analyses

No Comments

No Known Activations