INDEX

Explanations

instructions related to managing test cases and configurations in software testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

luß

-0.77

(!)

-0.69

Tembelea

-0.67

 thingy

-0.67

 shitty

-0.66

存于互联网档案馆

-0.66

 发表于

-0.66

 FUCKING

-0.66

Jereo

-0.65

 googling

-0.65

POSITIVE LOGITS

 becauſe

0.60

 ſtand

0.59

您可以

0.59

 neceſſ

0.57

ſy

0.56

 ſon

0.56

 chofe

0.55

})}

0.55

 ſtill

0.55

 whoſe

0.55

Activations Density 0.511%

instructions related to managing test cases and configurations in software testing

No Comments

No Known Activations