INDEX

Explanations

phrases indicating negation or a lack of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

PhysRev

-0.79

vábbi

-0.68

 copii

-0.66

onsored

-0.65

 disambiguazione

-0.63

 frumos

-0.63

 aastal

-0.59

 employe

-0.58

 kwanza

-0.58

 whereof

-0.57

POSITIVE LOGITS

rolid

0.74

 McQu

0.73

 certainly

0.72

argli

0.70

 indeed

0.70

 bukan

0.68

abelle

0.68

yntax

0.67

 Bukan

0.65

twimg

0.64

Activations Density 0.013%

phrases indicating negation or a lack of something

No Comments

No Known Activations