INDEX

Explanations

references to personal experiences and updates in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Personensuche

-0.83

دانشنامهٔ

-0.78

 estimés

-0.70

 scattata

-0.68

 pinulongan

-0.65

hyrchwyd

-0.59

 Почему

-0.58

 Audiodateien

-0.58

 Зачем

-0.55

Ejemplos

-0.54

POSITIVE LOGITS

相変わらず

0.64

djangoproject

0.61

 Exciting

0.57

 continues

0.57

 continuing

0.56

OrWhiteSpace

0.56

FilterChain

0.56

Exciting

0.54

 Continuing

0.53

Continu

0.53

Activations Density 0.275%

references to personal experiences and updates in a narrative context

No Comments

No Known Activations