INDEX

Explanations

references to political entities, particularly countries and their governmental structures

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

Comes before names of countries/republics

np_acts-logits-general · gemini-2.0-flash

names of republics

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

 Empieza

-0.67

 Europy

-0.56

">//

-0.54

 <<<<<<<<<<<<<<

-0.53

 henvisninger

-0.52

 VIDEOTAPE

-0.52

InjectAttribute

-0.51

 Азии

-0.51

PyErr

-0.50

qrt

-0.49

POSITIVE LOGITS

 Republic

1.21

 republic

0.97

Republic

0.95

 REPUBLIC

0.87

 république

0.74

republic

0.74

 République

0.73

 United

0.72

 Empire

0.69

 Federation

0.67

Activations Density 0.319%

references to political entities, particularly countries and their governmental structures

Comes before names of countries/republics

names of republics

No Comments

No Known Activations