INDEX

Explanations

references to tributes and memorials related to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-0.80

Tembelea

-0.74

eafter

-0.74

 disambiguazione

-0.73

 calculées

-0.70

yntaxException

-0.68

ernalia

-0.68

 Monfieur

-0.68

 uſed

-0.66

BibitemShut

-0.66

POSITIVE LOGITS

 tribute

0.68

:(

0.65

 Tribute

0.61

 tribe

0.60

 cigarettes

0.59

TR

0.58

 cigarette

0.58

 Référence

0.57

 Cigarette

0.56

TR

0.55

Activations Density 0.211%

references to tributes and memorials related to individuals

No Comments

No Known Activations