INDEX

Explanations

specific fictional characters or entities from a specific narrative universe

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

rungsseite

-0.95

rrggbb

-0.81

 يتيمه

-0.73

 للاسماء

-0.65

posedge

-0.64

tvguidetime

-0.62

verwijspagina

-0.61

存于互联网档案馆

-0.59

UserScript

-0.59

 препратки

-0.57

POSITIVE LOGITS

 Pokémon

0.47

 pokemon

0.44

 Pokemon

0.43

pexpr

0.43

 Trainers

0.40

Pokemon

0.39

Pokémon

0.37

 trainers

0.35

pokemon

0.35

 ско

0.34

Activations Density 0.227%

specific fictional characters or entities from a specific narrative universe

No Comments

No Known Activations