INDEX

Explanations

references to equations or mathematical notations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

contentLoaded

-0.54

वार

-0.54

kezi

-0.53

жах

-0.51

BindingSource

-0.51

 Unit

-0.51

AutoField

-0.50

NOSTIC

-0.50

 tearDown

-0.50

stina

-0.49

POSITIVE LOGITS

 للمعارف

0.67

 مشين

0.64

 الرخصة

0.64

UrlResolution

0.60

 kasarigan

0.60

 above

0.60

 Pelop

0.59

viewDid

0.59

 itſelf

0.59

 Theſe

0.59

Activations Density 0.593%

references to equations or mathematical notations in the text

No Comments

No Known Activations