INDEX

Explanations

technical terminology and references related to programming or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

щихся

-0.49

WillAppear

-0.48

vs

-0.48

and

-0.47

」、「

-0.47

いたり

-0.47

」「

-0.46

）、

-0.46

”、“

-0.46

 orgánica

-0.45

POSITIVE LOGITS

uxxxx

1.03

 ویکی‌پدیای

0.89

 surla

0.86

VersionUID

0.81

yntaxException

0.72

imize

0.72

TypedDataSet

0.70

adaptiveStyles

0.68

Datuak

0.68

 समीक्षक

0.67

Activations Density 0.252%

technical terminology and references related to programming or data structures

No Comments

No Known Activations