INDEX

Explanations

comments and documentation in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

RenderAtEndOf

-1.05

acterium

-0.71

izr

-0.66

 Bundy

-0.61

󠁧

-0.59

mybatisplus

-0.57

imbur

-0.57

MessageTagHelper

-0.57

RDONLY

-0.57

 StatefulWidget

-0.56

POSITIVE LOGITS

 Wiktionnaire

0.56

 AssemblyVersion

0.55

 الاطلاع

0.54

*/

0.52

ंदीखरीदारी

0.52

ubourg

0.52

 ostavi

0.52

↵↵↵↵

0.52

 néz

0.51

THRESH

0.51

Activations Density 0.042%

comments and documentation in programming code

No Comments

No Known Activations