INDEX

Explanations

references to characters and storylines in film and television narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

\{\\

-0.82

EndInit

-0.68

 للاسماء

-0.64

rrggbb

-0.61

AndEndTag

-0.58

IsContent

-0.58

Попис

-0.57

 Meksiku

-0.57

 continúas

-0.57

Geplaatst

-0.56

POSITIVE LOGITS

 characters

0.71

 personaje

0.60

 character

0.59

 personnage

0.58

 Characters

0.57

 protagonist

0.57

 CHARACTERS

0.56

 mascot

0.54

 personaggio

0.54

 personagem

0.54

Activations Density 0.296%

references to characters and storylines in film and television narratives

No Comments

No Known Activations