INDEX

Explanations

negative sentiments or opposing viewpoints

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

 outer

-0.51

日閲覧

-0.50

êque

-0.50

gut

-0.49

 Bhatt

-0.48

nste

-0.48

 delivery

-0.48

 جریان

-0.47

 courant

-0.46

ook

-0.46

POSITIVE LOGITS

 المعيارى

0.78

########.

0.73

TagMode

0.68

EndInit

0.67

PerformLayout

0.66

Personensuche

0.65

 <=",

0.64

 للاسماء

0.60

 surla

0.59

 censiti

0.56

Activations Density 0.053%

negative sentiments or opposing viewpoints

No Comments

No Known Activations