INDEX

Explanations

references to specific reading devices or technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

+#+

-0.57

LayoutPanel

-0.53

حات

-0.51

Datuak

-0.50

Affiliation

-0.49

Legende

-0.49

parametrize

-0.49

histle

-0.48

 MonoBehaviour

-0.47

 explicado

-0.46

POSITIVE LOGITS

 Books

0.89

 books

0.87

 librarians

0.86

 librarian

0.84

 bookstore

0.84

books

0.82

 libraries

0.80

 Normdatei

0.80

 bookstores

0.79

Books

0.79

Activations Density 0.540%

references to specific reading devices or technologies

No Comments

No Known Activations