INDEX

Explanations

terms related to political and legal concepts, particularly focusing on implications and interpretations in governance and rights

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

followed by opinions or beliefs

np_acts-logits-general · gemini-2.0-flash

treats or regards as

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

 فريبيس

-0.73

AutoScaleMode

-0.73

 tartalomajánló

-0.71

 виправивши

-0.66

getColumnIndex

-0.64

 تضيفلها

-0.62

istoitu

-0.60

İstinadlar

-0.60

PostConstruct

-0.60

isContained

-0.59

POSITIVE LOGITS

 treat

1.47

 regarded

1.40

treat

1.36

 treating

1.34

 treats

1.30

 menganggap

1.30

 considers

1.29

 consider

1.29

 considérer

1.26

 regard

1.26

Activations Density 0.652%

terms related to political and legal concepts, particularly focusing on implications and interpretations in governance and rights

followed by opinions or beliefs

treats or regards as

No Comments

No Known Activations