INDEX

Explanations

references to notable individuals and their accomplishments or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tvguidetime

-0.59

 xung

-0.55

 Periodicals

-0.50

 Adults

-0.49

 spéciaux

-0.49

Semantics

-0.49

 particuliers

-0.49

omethane

-0.48

 handel

-0.48

łk

-0.48

POSITIVE LOGITS

 Canadian

1.54

 Australian

1.52

 Japanese

1.48

 Italian

1.43

 Israeli

1.43

 Mexican

1.42

 Brazilian

1.41

 Indonesian

1.39

 German

1.38

 Nigerian

1.37

Activations Density 1.095%

references to notable individuals and their accomplishments or attributes

No Comments

No Known Activations