INDEX

Explanations

references to notation or tagging in a mathematical context

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 createState

-0.47

 propOrder

-0.45

źć

-0.44

ymce

-0.43

RenderAtEndOf

-0.42

InstanceState

-0.42

FAT

-0.41

Parcelize

-0.41

 гг

-0.40

 Ceinture

-0.40

POSITIVE LOGITS

/******/

3.30

/***/

0.81

 ***!

0.75

****/

0.55

 للاسماء

0.55

">//

0.51

httphttps

0.51

Diweddarwch

0.47

 Cordero

0.46

******/

0.44

Activations Density 0.000%

references to notation or tagging in a mathematical context

No Comments

No Known Activations