INDEX

Explanations

references to central organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 comets

-0.79

 Dolom

-0.76

HRT

-0.76

 Prophets

-0.76

 Donegal

-0.74

 moons

-0.73

 Filipinas

-0.72

 Photon

-0.72

 Trooper

-0.72

 Uttarakhand

-0.71

POSITIVE LOGITS

 Central

1.44

Central

1.35

CENTRAL

1.23

 CENTRAL

1.23

 central

1.19

central

1.17

 centrales

1.01

Centr

0.99

 Centra

0.97

 centrale

0.93

Activations Density 0.044%

references to central organizations or entities

No Comments

No Known Activations