INDEX

Explanations

references to "government" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 Missile

-0.69

イケ

-0.69

 estoppel

-0.69

itemId

-0.68

 Dinah

-0.68

 Dior

-0.65

 trespassing

-0.65

 Ness

-0.64

 jitter

-0.64

 Alcott

-0.64

POSITIVE LOGITS

 Government

1.70

Government

1.54

 government

1.49

 GOVERNMENT

1.30

vernment

1.27

government

1.27

GOVERNMENT

1.25

 Governments

1.21

 Govt

1.20

 governments

1.20

Activations Density 0.056%

references to "government" and related terms

No Comments

No Known Activations