INDEX

Explanations

references to programming or coding constructs

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

Spoljašnje

-0.64

"><!--

-0.63

\"></

-0.62

="<?=$

-0.61

Eureka

-0.59

#![

-0.57

 ""],

-0.56

 Eureka

-0.55

 uſed

-0.55

webElement

-0.54

POSITIVE LOGITS

multirow

0.83

!*\

0.81

 rowspan

0.79

 Affiliations

0.76

ConstraintMaker

0.73

 numerus

0.67

LabelTagHelper

0.67

 وتسجيلات

0.62

PositiveButton

0.61

abstractmethod

0.60

Activations Density 0.009%

references to programming or coding constructs

No Comments

No Known Activations