INDEX

Explanations

phrases related to processes or conditions involving interactions or relationships, particularly in a scientific or procedural context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Camar

-0.47

em

-0.46

 suci

-0.43

brido

-0.43

 concluded

-0.42

Brid

-0.42

 them

-0.42

 matel

-0.41

 majority

-0.40

PageIndex

-0.40

POSITIVE LOGITS

IntoConstraints

0.87

NameInMap

0.80

UnsafeEnabled

0.78

Personendaten

0.74

aarrggbb

0.72

isque

0.71

MLLoader

0.70

SPATH

0.67

VersionUID

0.66

XmlAccessorType

0.65

Activations Density 0.475%

phrases related to processes or conditions involving interactions or relationships, particularly in a scientific or procedural context

No Comments

No Known Activations