INDEX

Explanations

references to technological devices and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 EdgeInsets

-0.64

acherous

-0.64

onded

-0.57

awaiter

-0.56

urtles

-0.56

 opérateurs

-0.54

ubourg

-0.54

aternion

-0.53

labas

-0.53

ؤلاء

-0.53

POSITIVE LOGITS

OGND

0.70

これからも

0.59

Cyfarwyddwr

0.58

 transfieras

0.57

IndentedString

0.54

 myself

0.51

 resourceCulture

0.50

0.49

 tartalomajánló

0.48

AndroidJUnit

0.48

Activations Density 0.295%

references to technological devices and their features

No Comments

No Known Activations