INDEX

Explanations

references to programming objects and their associated properties or methods

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

GraphicsUnit

-0.94

httphttps

-0.70

 GenerationType

-0.69

viewDidLoad

-0.65

 Chio

-0.65

 giusti

-0.64

 bienven

-0.63

}^{(\

-0.63

 koron

-0.62

 consag

-0.61

POSITIVE LOGITS

 objects

2.00

 object

1.96

 Object

1.81

 Objects

1.81

 OBJECT

1.78

objects

1.74

object

1.68

Objects

1.61

Object

1.59

OBJECT

1.52

Activations Density 0.079%

references to programming objects and their associated properties or methods

No Comments

No Known Activations