INDEX

Explanations

segments indicating a forceful initiation action

oai_token-act-pair · o3-mini Triggered by @yemengyus1

references to kicking actions or related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 مشين

-0.57

PageIndex

-0.56

 Morde

-0.54

moveToFirst

-0.53

 Olivenöl

-0.51

ReusableCell

-0.51



-0.50

 BoxFit

-0.50

出版年

-0.49

fficacy

-0.48

POSITIVE LOGITS

XmlAccessType

0.75

 kicks

0.75

InitVars

0.73

 kick

0.70

 Kicks

0.70

 dedicated

0.69

Dedicated

0.68

kick

0.68

 kicking

0.68

,:);

0.66

Activations Density 0.095%

segments indicating a forceful initiation action

references to kicking actions or related terminology

No Comments

No Known Activations