INDEX

Explanations

legal terms and concepts related to awards and intellectual property rights

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

Awards, permissions, or authorizations

np_acts-logits-general · gemini-2.0-flash

awards and privileges granted

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

COUVER

-0.49

FunctionFlags

-0.47

miques

-0.47

 Theodo

-0.43

kirch

-0.43

multirow

-0.43

webElementXpaths

-0.43

README

-0.42

tangentMode

-0.42

poto

-0.42

POSITIVE LOGITS

 awarded

1.51

 awarding

1.40

 granted

1.34

 granting

1.32

 otorg

1.30

 bestowed

1.29

 conferred

1.27

 bestow

1.24

 Awarded

1.21

 vergeben

1.19

Activations Density 0.396%

legal terms and concepts related to awards and intellectual property rights

Awards, permissions, or authorizations

awards and privileges granted

No Comments

No Known Activations