INDEX

Explanations

references to specific scientific terms or entities related to academic or research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

NGC

-0.65

EndGlobalSection

-0.64

Personensuche

-0.59

 مرئيه

-0.57

 latine

-0.54

verifyException

-0.54

 Wiktionnaire

-0.53

thrower

-0.53

 Thessalon

-0.52

们的

-0.52

POSITIVE LOGITS

ura

0.85

+#+#

0.84

URA

0.74

oura

0.70

StoryboardSegue

0.66

Portail

0.65

最快更新

0.63

%");

0.62

StackNavigator

0.61

 Myra

0.61

Activations Density 0.042%

references to specific scientific terms or entities related to academic or research contexts

No Comments

No Known Activations