INDEX

Explanations

references to specific dates and numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

(),

-0.57

 JpaRepository

-0.54

).]

-0.50

(||

-0.50

󠁣

-0.49

CloseOperation

-0.48

 Wich

-0.48

 Stande

-0.48

()");

-0.48

 Lage

-0.48

POSITIVE LOGITS

 Paglinawan

1.01

rawDesc

0.81

 gezet

0.70

 HasFactory

0.67

ellite

0.66

ArrowToggle

0.66

 саны

0.64

lawayo

0.63

phorbia

0.62

 autorytatywna

0.60

Activations Density 0.529%

references to specific dates and numerical values

No Comments

No Known Activations