INDEX

Explanations

references to different modes or types, particularly in a technical or programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

?>

-0.74

springframework

-0.70

************

-0.67

ിച്ച

-0.63

 Bellas

-0.63

addContainerGap

-0.63

 fluorine

-0.63

?></

-0.61

 Kear

-0.61

アリング

-0.61

POSITIVE LOGITS

 Mode

1.92

 mode

1.82

 modes

1.81

 MODE

1.81

mode

1.80

modes

1.78

 Modes

1.78

Mode

1.71

Modes

1.67

MODE

1.60

Activations Density 0.046%

references to different modes or types, particularly in a technical or programming context

No Comments

No Known Activations