INDEX

Explanations

passive voice constructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PerformLayout

-0.99

UserScript

-0.85

 الرياضيه

-0.80

UnusedPrivate

-0.70

expandindo

-0.68

 purpoſe

-0.67

ImageContext

-0.65

GEBURTSDATUM

-0.65

Попис

-0.65

MemoryWarning

-0.63

POSITIVE LOGITS

can

1.06

 easily

1.02

也可

0.92

CanBe

0.91

 Puede

0.89

 puede

0.87

 dapat

0.83

kan

0.81

easily

0.80

 võib

0.79

Activations Density 0.146%

passive voice constructions

No Comments

No Known Activations