INDEX

Explanations

references to shapes and geometry

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

 Munro

-0.85

 acorns

-0.83

wój

-0.78

'/>

-0.77

例句

-0.76

SpringRunner

-0.74

 MenuView

-0.74

crollView

-0.74

 trouvera

-0.74

 Antara

-0.72

POSITIVE LOGITS

 shape

2.51

 shapes

2.32

 SHAPE

2.29

 Shape

2.28

shape

2.26

Shape

2.15

 Shapes

2.11

SHAPE

2.11

shapes

2.05

 shaped

1.89

Activations Density 0.065%

references to shapes and geometry

No Comments

No Known Activations