INDEX

Explanations

technical terms and specifications related to programming and computer architecture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 فريبيس

-0.76

StructEnd

-0.70

 Exactos

-0.68

DeleteBehavior

-0.67

celotti

-0.64

-0.62

Sucesor

-0.61

 MaterialApp

-0.61

HomeAsUpEnabled

-0.60

adaptiveStyles

-0.60

POSITIVE LOGITS

modelBuilder

0.56

xnn

0.55

 autorytatywna

0.55

fæ

0.50

}{*}{

0.48

]){

0.46

urig

0.45

fjspx

0.45

angan

0.45

ValueStyle

0.45

Activations Density 0.562%

technical terms and specifications related to programming and computer architecture

No Comments

No Known Activations