INDEX

Explanations

references to specific entities, particularly involving the term "Az" and certain symbols in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 OMITTED

-0.54

 ſever

-0.51

 INCOR

-0.51

Kirch

-0.50

AntiForgeryToken

-0.49

 newList

-0.49

mogorov

-0.48

 Mord

-0.48

 photolibrary

-0.48

ंप

-0.48

POSITIVE LOGITS

Personendaten

0.84

the

0.76

 متعلقه

0.75

بوابة

0.72

 Hongrie

0.71

 aload

0.70

 Pyle

0.68

az

0.68

 للمعارف

0.68

 useSelector

0.65

Activations Density 0.066%

references to specific entities, particularly involving the term "Az" and certain symbols in programming contexts

No Comments

No Known Activations