INDEX

Explanations

technical definitions and explanations, particularly concerning terms and concepts in formal documents or academic discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.56

 rahasia

-0.52

 المعيارى

-0.50

Esperamos

-0.49

 صوتيه

-0.48

ISupport

-0.48

anco

-0.48

 insuffisamment

-0.45

ungkinan

-0.45

Anhalt

-0.45

POSITIVE LOGITS

 definition

3.65

 definitions

3.23

definition

3.03

 Definition

3.02

 defined

2.95

 define

2.87

Definition

2.83

定義

2.73

 Definitions

2.71

 définition

2.70

Activations Density 0.791%

technical definitions and explanations, particularly concerning terms and concepts in formal documents or academic discussions

No Comments

No Known Activations