INDEX

Explanations

references to the name "Je" in various contexts

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

"Je" followed by a word

np_acts-logits-general · gemini-2.0-flash

Je followed by French verbs

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

 समीक्षाओं

-0.98

NameInMap

-0.95

windowFixed

-0.91

uxxxx

-0.90

Personendaten

-0.89

 arşivlendi

-0.88

 Normdatei

-0.87

发表于

-0.85

RegistryLite

-0.85

 تضيفلها

-0.84

POSITIVE LOGITS

Jez

0.57

Je

0.56

 suis

0.53

Je

0.46

ộ

0.44

EEP

0.42

retra

0.39

jeje

0.38

Gom

0.38

 acrylique

0.38

Activations Density 0.097%

references to the name "Je" in various contexts

"Je" followed by a word

Je followed by French verbs

No Comments

No Known Activations