INDEX

Explanations

phrases and actions related to problem-solving and coping mechanisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

دانشنامهٔ

-0.64

Personensuche

-0.61

elemField

-0.56

 ProtoMessage

-0.55

Хьажоргаш

-0.54

पा

-0.53

 commission

-0.52

toje

-0.51

}{*}{

-0.50

 Synag

-0.50

POSITIVE LOGITS

 workaround

0.99

 tolerated

0.69

 survival

0.68

survival

0.67

 Survival

0.66

 survive

0.66

 SURV

0.65

 surviving

0.64

survi

0.63

 makeshift

0.62

Activations Density 0.189%

phrases and actions related to problem-solving and coping mechanisms

No Comments

No Known Activations