INDEX

Explanations

references to plates and related objects in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 مؤرشف

-0.75

 GenerationType

-0.74

FieldBuilder

-0.72

']));

-0.72

 Himo

-0.71

-0.68

حيط

-0.68

)?;

-0.68

 ")";

-0.67

près

-0.67

POSITIVE LOGITS

 plates

2.70

 plate

2.55

 Plates

2.50

 Plate

2.46

plate

2.34

 PLATE

2.33

Plates

2.31

 PLATES

2.30

Plate

2.29

plates

2.29

Activations Density 0.049%

references to plates and related objects in a variety of contexts

No Comments

No Known Activations