INDEX

Explanations

references to individuals in positions of authority, particularly in legal and governmental contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

 مُعرِّف

-0.74

 Мексичка

-0.64

WriteTagHelper

-0.56

 CreateTagHelper

-0.54

 /\.(

-0.54

"])

-0.54

τύ

-0.53

 Vikipedi

-0.52

+#+#

-0.52

 дописавши

-0.52

POSITIVE LOGITS

 Chief

1.50

 president

1.49

 President

1.46

 chief

1.44

CEO

1.42

 chairman

1.42

 Chairman

1.39

 Director

1.36

Chief

1.33

 director

1.26

Activations Density 0.636%

references to individuals in positions of authority, particularly in legal and governmental contexts

No Comments

No Known Activations