INDEX

Explanations

technical terms and concepts related to software development and frameworks

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MemoryWarning

-0.56

HomeAsUpEnabled

-0.47

WithIdentifier

-0.45

رأ

-0.44

 çiz

-0.43

 great

-0.42

NgModule

-0.42

escens

-0.41

γγ

-0.40

 cumpri

-0.40

POSITIVE LOGITS

BeginContext

0.77

OGND

0.72

Personensuche

0.68

 okuyayım

0.67

oa̍t

0.67

Spoljašnje

0.66

 <>",

0.66

出版年

0.65

SharedDtor

0.65

 snippetHide

0.64

Activations Density 0.716%

technical terms and concepts related to software development and frameworks

No Comments

No Known Activations