INDEX

Explanations

code structures and constructs related to function definitions and control flow in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 Paglinawan

-0.55

 kasarigan

-0.53

OGND

-0.47

 autorytatywna

-0.44

 TextFormField

-0.43

kebox

-0.42

GEBURTSDATUM

-0.42

 OMITBAD

-0.42

vrons

-0.42

endregion

-0.42

POSITIVE LOGITS

 Engel

0.71

 Vogel

0.69

 Joel

0.69

 pixel

0.68

 trail

0.68

Engel

0.68

Joel

0.67

 council

0.66

 hotel

0.65

 seal

0.64

Activations Density 0.465%

code structures and constructs related to function definitions and control flow in programming

No Comments

No Known Activations