INDEX

Explanations

references to specific people or characters involved in a narrative or discussion

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

webElementGuid

-0.44

})();

-0.43

ReusableCell

-0.42

الحياه

-0.42

 ExecuteAsync

-0.40

"}}>

-0.40

ChildScrollView

-0.40

 iprot

-0.40

Tikang

-0.40

RenderAtEndOf

-0.38

POSITIVE LOGITS

makeConstraints

0.47

 betweenstory

0.45

WireFormatLite

0.43

modelBuilder

0.42

IsContent

0.40

homonymie

0.40

gjenge

0.40

اریخ

0.39

migrationBuilder

0.39

рыя

0.37

Activations Density 1.896%

references to specific people or characters involved in a narrative or discussion

No Comments

No Known Activations