INDEX

Explanations

words or phrases related to deception or manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

mmä

-0.41

getOut

-0.36

 wonder

-0.35

 perso

-0.35

 ExecuteAsync

-0.34

icina

-0.34

 diligence

-0.34

 faim

-0.34

 Wonder

-0.33

 memor

-0.33

POSITIVE LOGITS

 مشين

0.96

Personensuche

0.93

tagHelperRunner

0.80

 للاسماء

0.78

 utafitiHapana

0.76

webElementGuid

0.73

kháu

0.73

HostException

0.72

XmlAccessType

0.71

ArrowToggle

0.71

Activations Density 0.262%

words or phrases related to deception or manipulation

No Comments

No Known Activations