INDEX

Explanations

rhetorical questions that express curiosity or challenge beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Haller

-0.75

-0.71

intahan

-0.70

 Cortes

-0.70

Hauptartikel

-0.69

")[

-0.67

INSTALLED

-0.67

.\

-0.66

PEZ

-0.66

 Schot

-0.66

POSITIVE LOGITS

 Whyte

1.60

why

1.53

why

1.50

Why

1.48

Why

1.43

WHY

1.37

WHY

1.35

 Warum

1.27

 Waarom

1.23

 pourquoi

1.17

Activations Density 0.041%

rhetorical questions that express curiosity or challenge beliefs

No Comments

No Known Activations