INDEX

Explanations

specific mathematical symbols and operators used in expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 itſelf

-0.77

 Мексичка

-0.76

 himſelf

-0.70

 Jefus

-0.67

AndroidJUnit

-0.65

 Theſe

-0.65

 Majefty

-0.64

Efq

-0.64

 againſt

-0.62

ſelf

-0.62

POSITIVE LOGITS

UnknownFieldSet

0.79

StoryboardSegue

0.64

findpost

0.64

&&

0.62

))).

0.59

})+\

0.56

↵

0.55

&&

0.54

 مرئيه

0.54

 препратки

0.54

Activations Density 0.759%

specific mathematical symbols and operators used in expressions

No Comments

No Known Activations