INDEX

Explanations

mentions of awards and recognitions

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

Awards, honors, or recognition received

np_acts-logits-general · gemini-2.0-flash

people awarded honors prizes

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

grà

-0.58

AddRange

-0.55

 Audiodateien

-0.53

 تضيفلها

-0.52

FileInput

-0.49

 跳转至

-0.49

ArgumentParser

-0.47

ibase

-0.46

SceneManagement

-0.45

fycat

-0.45

POSITIVE LOGITS

 honorary

0.90

 Commande

0.80

 Honorary

0.76

 Order

0.73

Honorary

0.71

 Lifetime

0.69

 lifetime

0.68

Commande

0.67

WriteBarrier

0.66

 Chevalier

0.66

Activations Density 0.206%

mentions of awards and recognitions

Awards, honors, or recognition received

people awarded honors prizes

No Comments

No Known Activations