INDEX

Explanations

technical terms and references related to computer programming and graphics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 vold

-0.84

'])){

-0.80

<h2>

-0.79

'){

-0.77

'}>

-0.77

الإنجليزية

-0.72

"){

-0.72

 nahilalakip

-0.72

nment

-0.71

Advertisement

-0.71

POSITIVE LOGITS

 Pollut

0.92

 Atty

0.89

httphttps

0.88

 meds

0.87

 Bucs

0.86

 GONNA

0.86

 mags

0.85

 Champs

0.83

yrs

0.83

yrs

0.82

Activations Density 0.750%

technical terms and references related to computer programming and graphics

No Comments

No Known Activations