INDEX

Explanations

elements related to television networks and broadcasting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

RectangleBorder

-0.73

 NSCoder

-0.68

 écoulé

-0.67

 تضيفلها

-0.63

DeleteBehavior

-0.63

 RSSSF

-0.62

DrawerToggle

-0.61

IMS

-0.60

mmate

-0.58

cellona

-0.57

POSITIVE LOGITS

 television

0.74

 broadcasting

0.71

 broadcast

0.71

 broadcasters

0.70

 broadcasts

0.68

TV

0.66

 Television

0.64

 televis

0.61

 cable

0.60

television

0.59

Activations Density 0.175%

elements related to television networks and broadcasting

No Comments

No Known Activations