INDEX

Explanations

concepts related to definitions and distinctions in various fields

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

Definitions and defining

np_acts-logits-general · gemini-2.0-flash

providing definitions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

GeneratedCode

-0.55

 predicted

-0.52

Życiorys

-0.51

Unavailable

-0.49

Pautan

-0.49

deve

-0.47

 favori

-0.47

Aholisi

-0.46

DeleteBehavior

-0.46

komendasi

-0.46

POSITIVE LOGITS

 definition

1.63

 definitions

1.53

definition

1.33

 Definition

1.29

 Definitions

1.27

定義

1.21

 Defining

1.21

 define

1.21

 distinction

1.18

Defining

1.17

Activations Density 0.651%

concepts related to definitions and distinctions in various fields

Definitions and defining

providing definitions

No Comments

No Known Activations