INDEX

Explanations

references to journals and publications

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 espèce

-0.83

 Roskov

-0.82

 Cæsar

-0.77

 Turch

-0.73

 Referential

-0.71

 définiti

-0.69

 Pliny

-0.69

 Spokes

-0.68

 météo

-0.68

 taches

-0.67

POSITIVE LOGITS

 BrowserRouter

0.89

lawayo

0.84

ation

0.81

 Journal

0.80

 march

0.79

 March

0.78

 Portail

0.78

ніципа

0.76

scho

0.75

 MARCH

0.74

Activations Density 0.115%

references to journals and publications

No Comments

No Known Activations