INDEX

Explanations

references to conflict or acts of aggression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

tvguidetime

-0.54

ThroughAttribute

-0.52

ArgsConstructor

-0.50

ίδι

-0.50

homonymie

-0.50

Global

-0.49

 continents

-0.49

nosa

-0.49

 global

-0.48

 globales

-0.48

POSITIVE LOGITS

 rebels

0.73

 executions

0.71

 insurrection

0.71

 uprising

0.71

 revolt

0.70

 guerrillas

0.70

 riots

0.69

 guerrilla

0.69

 rebellion

0.68

 bandits

0.67

Activations Density 0.856%

references to conflict or acts of aggression

No Comments

No Known Activations