INDEX

Explanations

key figures and numerical data in regard to security protocols and defenses in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\}\\

-0.46

}:=\

-0.46

,:]

-0.46

ArgsConstructor

-0.44

kadi

-0.44

]<<"

-0.44

ву

-0.43

 tủ

-0.43

lès

-0.43

ından

-0.42

POSITIVE LOGITS

KURZBESCHREIBUNG

0.77

 дописавши

0.73

 BrowserModule

0.67

 GenerationType

0.65

 InputDecoration

0.65

 تضيفلها

0.65

 Jefus

0.64

 itſelf

0.62

Efq

0.60

 snippetHide

0.60

Activations Density 1.347%

key figures and numerical data in regard to security protocols and defenses in various contexts

No Comments

No Known Activations