INDEX

Explanations

grammatical structures and phrases related to nouns and their usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Bowers

-0.70

 Lewis

-0.70

 Bernal

-0.68

POM

-0.67

 Karn

-0.66

 Dodson

-0.66

 Hawthorne

-0.66

 Leviathan

-0.66

Ved

-0.64

Lewis

-0.63

POSITIVE LOGITS

 Justin

0.93

Justin

0.86

 justin

0.85

 Bree

0.84

Bree

0.81

Pai

0.76

justin

0.71

 Mandy

0.71

 Talla

0.70

 Kele

0.69

Activations Density 1.402%

grammatical structures and phrases related to nouns and their usage

No Comments

No Known Activations