INDEX

Explanations

terms related to the recognition and classification of projects or programs at various administrative levels

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

geographical divisions

np_acts-logits-general · gemini-2.0-flash

national, local, regional, international

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

 ModelExpression

-0.54

Havolalar

-0.53

 Walkover

-0.52

PhysRevD

-0.47

 Dramatic

-0.46

veget

-0.46

хани

-0.46

rawDesc

-0.44

र्त

-0.44

 aapt

-0.44

POSITIVE LOGITS

 national

1.97

 local

1.93

 regional

1.88

 nationally

1.86

 global

1.82

 locally

1.75

 regionally

1.75

local

1.70

 international

1.68

national

1.67

Activations Density 0.487%

terms related to the recognition and classification of projects or programs at various administrative levels

geographical divisions

national, local, regional, international

No Comments

No Known Activations