INDEX

Explanations

references to actors and their achievements

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

About acting and actors

np_acts-logits-general · gemini-2.0-flash

actors and acting

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تضيفلها

-0.63

Datuak

-0.62

міністра

-0.60

 AssemblyCompany

-0.60

 TestBed

-0.59

 linkovi

-0.58

 geométrico

-0.58

EndGlobalSection

-0.57

DockStyle

-0.56

RenderAtEndOf

-0.56

POSITIVE LOGITS

 acting

1.91

 actor

1.91

 actors

1.85

 Actors

1.73

 Acting

1.61

Acting

1.60

 Actor

1.60

Actors

1.57

 actress

1.53

acting

1.53

Activations Density 0.221%

references to actors and their achievements

About acting and actors

actors and acting

No Comments

No Known Activations