INDEX

Explanations

terms related to control and authority, particularly in political or systemic contexts

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•korean

kinda polite

No Comments

Negative Logits

Personensuche

-1.95

 Савезне

-1.61

 Мексичка

-1.56

tagHelperRunner

-1.54

 autorytatywna

-1.40

:✨

-1.36

adaptiveStyles

-1.23

kloped

-1.22

Datuak

-1.20

setVerticalGroup

-1.18

POSITIVE LOGITS

 […]

1.11

↵

0.90

...

0.89

0.86

…

0.79

...

0.79

0.72

 [...]

0.71

0.70

Activations Density 93.003%

terms related to control and authority, particularly in political or systemic contexts

No Comments

No Known Activations