INDEX

Explanations

technical terms and structures related to programming and computational algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

mino

-0.46

 getClass

-0.45

XmlAccessorType

-0.45

arg

-0.44

artment

-0.43

 Eich

-0.42

dataclass

-0.42

StoryboardSegue

-0.42

 fianco

-0.41

mintaan

-0.41

POSITIVE LOGITS

mergeFrom

0.81

 חיצוניים

0.73

 betweenstory

0.70

WithIOException

0.68

SharedDtor

0.67

ArrowToggle

0.67

 Roskov

0.66

ectoria

0.66

EndGlobalSection

0.65

setVerticalGroup

0.65

Activations Density 0.524%

technical terms and structures related to programming and computational algorithms

No Comments

No Known Activations