INDEX

Explanations

references to uniformity or uniform distributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

wisata

-0.83

########.

-0.83

 useContext

-0.82

 henvisninger

-0.78

 ControllerBase

-0.75

WAUKEE

-0.74

ValueStyle

-0.74

 Juga

-0.72

RuleContext

-0.72

PhysRevLett

-0.72

POSITIVE LOGITS

 uniform

1.70

Uniform

1.63

uniform

1.62

 Uniform

1.59

 uniforms

1.46

 uniformity

1.40

IFORM

1.32

iforms

1.28

 uniformes

1.27

 uniforme

1.22

Activations Density 0.116%

references to uniformity or uniform distributions

No Comments

No Known Activations