INDEX

Explanations

details and development of fictional characters, as well as their relationships and dynamics within narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Roskov

-0.66

AccessFile

-0.62

IsContent

-0.52

nissen

-0.51

 Diony

-0.51

bular

-0.50

 itſelf

-0.50

webElementXpaths

-0.48

出版年

-0.48

 inflater

-0.48

POSITIVE LOGITS

 characters

0.85

 character

0.75

 personnage

0.71

 fictional

0.68

 whom

0.67

LogFactory

0.67

 protagonist

0.66

 Characters

0.66

 CHARACTERS

0.66

 personaje

0.66

Activations Density 0.274%

details and development of fictional characters, as well as their relationships and dynamics within narratives

No Comments

No Known Activations