INDEX

Explanations

indicators of programming or coding syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

kháu

-0.82

RRect

-0.77

 дописавши

-0.76

endpush

-0.68

__':

-0.68

 Wiktionnaire

-0.67

CppMethod

-0.67

basicConfig

-0.66

didSet

-0.64

POSITIVE LOGITS

Hentet

0.46

 resourceCulture

0.42

GEBURTSDATUM

0.41

;->

0.39

 Groß

0.39

 totul

0.38

dicionado

0.37

页面存档备份

0.37

 cử

0.36

 بيها

0.36

Activations Density 0.614%

indicators of programming or coding syntax

No Comments

No Known Activations