INDEX

Explanations

elements related to media and entertainment, particularly those showcasing excellence or popularity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

جمعیت

-0.59

 Normdatei

-0.58

@[+][

-0.56

 berço

-0.56

bootstrapcdn

-0.55

 hereof

-0.54

such

-0.54

something

-0.53

 similar

-0.53

similar

-0.53

POSITIVE LOGITS

tagHelper

0.70

+#+#

0.67

own

0.64

intellij

0.63

 MatDialog

0.62

tvguidetime

0.60

 FormsModule

0.59

BorderFactory

0.57

BindingResult

0.55

liest

0.54

Activations Density 0.404%

elements related to media and entertainment, particularly those showcasing excellence or popularity

No Comments

No Known Activations