INDEX

Explanations

elements related to programming structures, particularly in code documentation and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

出版年

-0.72

 BoxDecoration

-0.53

 hänen

-0.52

migrationBuilder

-0.48

 leſs

-0.47

 himſelf

-0.47

 Eros

-0.45

 acoper

-0.43

 pietre

-0.43

 whoſe

-0.43

POSITIVE LOGITS

SourceChecksum

1.08

fjspx

0.90

ftagPool

0.83

RTLD

0.79

 tartalomajánló

0.79

styleType

0.73

NameInMap

0.73

AddHtmlAttribute

0.73

 mergeFrom

0.72

Portale

0.71

Activations Density 0.101%

elements related to programming structures, particularly in code documentation and definitions

No Comments

No Known Activations