INDEX

Explanations

references to global events, particularly related to world wars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 InputDecoration

-0.81

 desta

-0.80

 Pilate

-0.79

Xie

-0.78

 Pelosi

-0.77

 Mortar

-0.76

 Amtrak

-0.75

 Cottages

-0.73

 Ryanair

-0.73

 Notary

-0.73

POSITIVE LOGITS

 World

2.32

World

2.07

 WORLD

2.04

 world

1.95

WORLD

1.89

world

1.80

 Worlds

1.61

orld

1.56

Worlds

1.49

 worlds

1.48

Activations Density 0.044%

references to global events, particularly related to world wars

No Comments

No Known Activations