INDEX

Explanations

mathematical symbols and notations related to functions and variables

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

HasForeignKey

-0.67

τουργ

-0.64

Bibliographie

-0.61

GoogleMap

-0.56

DropTable

-0.55

 puro

-0.53

 Dunn

-0.52

CADE

-0.52

 otomatig

-0.52

ItemLayout

-0.51

POSITIVE LOGITS

 éché

0.66

Autoritní

0.62

 EconPapers

0.62

 محفوظة

0.62

 NSCoder

0.58

enumi

0.57

 onAnimation

0.56

 متعلقه

0.54

 OFDb

0.54

+#+#

0.53

Activations Density 0.821%

mathematical symbols and notations related to functions and variables

No Comments

No Known Activations