INDEX

Explanations

terms related to questions and their corresponding responses in a quiz or questionnaire format

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

XML or HTML tags

np_acts-logits-general · gemini-2.0-flash

French Q&A structure

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 dévelo

-0.66

 ainfi

-0.66

 nôtre

-0.61

 rechange

-0.61

 fidé

-0.61

 recev

-0.58

 réfrig

-0.57

 plufieurs

-0.55

 mauva

-0.55

 cérami

-0.53

POSITIVE LOGITS

nb

0.63

 French

0.54

 pour

0.54

 french

0.54

Fonction

0.53

 Drapeau

0.53

liste

0.52

nb

0.51

Erreur

0.50

Dé

0.49

Activations Density 0.148%

terms related to questions and their corresponding responses in a quiz or questionnaire format

XML or HTML tags

French Q&A structure

No Comments

No Known Activations