INDEX

Explanations

keywords related to type definitions and template usage in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 copii

-0.62

 joaat

-0.59

 Fiscalía

-0.58

useEffect

-0.58

 kvinder

-0.57

bitos

-0.55

%%

-0.55

bbene

-0.55

 Zeta

-0.55

 testigo

-0.54

POSITIVE LOGITS

typedef

0.95

 дописавши

0.79

stateProvider

0.76

posedge

0.75

</caption>

0.75

EndGlobalSection

0.71

issex

0.71

AccessorTable

0.71

 Roskov

0.70

 DriverManager

0.69

Activations Density 0.034%

keywords related to type definitions and template usage in programming

No Comments

No Known Activations