INDEX

Explanations

references to the term "ze," particularly in various contexts

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

 MainAxisSize

-0.74

 <=",

-0.70

 PopupWindow

-0.69

جغرافيا

-0.68

istoitu

-0.68

 تانيه

-0.67

Vidite

-0.67

 lenker

-0.64

ьажоргаш

-0.63

mobileqq

-0.62

POSITIVE LOGITS

Ze

0.49

0.47

Ze

0.47

катери

0.46

0.45

 doPost

0.45

ruptedException

0.45

IsPostBack

0.44

yorum

0.44

//

0.43

Activations Density 0.108%

references to the term "ze," particularly in various contexts

No Comments

No Known Activations