INDEX

Explanations

references to authors and their literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 estimés

-0.73

SequentialGroup

-0.70

numerusform

-0.65

ArrowToggle

-0.64

TagHelper

-0.64

 Audiodateien

-0.63

ParallelGroup

-0.63

日閲覧

-0.61



-0.61

ѓ

-0.60

POSITIVE LOGITS

 book

2.59

 books

2.35

book

2.03

 libro

1.85

books

1.83

 livro

1.75

 Book

1.71

 BOOK

1.67

Book

1.66

 buku

1.61

Activations Density 0.366%

references to authors and their literary works

No Comments

No Known Activations