INDEX

Explanations

terms related to technical programming or markup syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

tisgarh

-0.49

openConnection

-0.47

BackStack

-0.46

fieldLabel

-0.45

 Bioaccumulative

-0.43

 stanovnika

-0.42

yet

-0.40

liferay

-0.38

 compi

-0.38

 ambientale

-0.38

POSITIVE LOGITS

Efq

0.68

NUMX

0.67

 fieldNum

0.67

 Broom

0.65

Dux

0.65

 itſelf

0.64

 viewDidLoad

0.64

 initWithFrame

0.63

 broom

0.63

 nonatomic

0.62

Activations Density 0.339%

terms related to technical programming or markup syntax

No Comments

No Known Activations