INDEX

Explanations

references to objects in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.93

 GenerationType

-0.71

 Chio

-0.63

 koron

-0.63

 bienven

-0.62

 giusti

-0.62

}^{(\

-0.62

httphttps

-0.61

viewDidLoad

-0.61

omla

-0.61

POSITIVE LOGITS

 objects

1.91

 object

1.85

 Object

1.75

 Objects

1.74

 OBJECT

1.70

objects

1.67

object

1.57

Objects

1.56

Object

1.51

OBJECT

1.45

Activations Density 0.084%

references to objects in programming contexts

No Comments

No Known Activations