INDEX

Explanations

abbreviations and acronyms related to scientific terminology and measurement

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

 estimés

-0.84

aarrggbb

-0.83

mybatisplus

-0.79

Slf

-0.77

 ***!

-0.77

)}</

-0.76

 defaultstate

-0.74

!*\

-0.73

دانشنامهٔ

-0.73

)}>

-0.72

POSITIVE LOGITS

 zelve

0.78

 jellemző

0.75

drawiam

0.74

 GoogleFonts

0.74

Kjelder

0.73

ССР

0.73

 Majesté

0.71

ctx

0.70

 négatif

0.70

 feroit

0.70

Activations Density 1.720%

abbreviations and acronyms related to scientific terminology and measurement

No Comments

No Known Activations