INDEX

Explanations

references to objects in programming or data structures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GraphicsUnit

-0.91

 GenerationType

-0.80

}^{(\

-0.70

 giusti

-0.69

 bienven

-0.69

 koron

-0.67

 réguli

-0.66

 Chio

-0.66

CDS

-0.66

 Nacionales

-0.65

POSITIVE LOGITS

 objects

1.85

 object

1.82

 Object

1.71

 Objects

1.63

objects

1.61

 OBJECT

1.61

Objects

1.53

object

1.52

Object

1.47

OBJECT

1.41

Activations Density 0.078%

references to objects in programming or data structures

No Comments

No Known Activations