INDEX

Explanations

references to online platforms and user behavior in digital environments

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

users or user experience

np_acts-logits-general · gemini-2.0-flash

their user

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

bufio

-0.41

 menye

-0.37

Mult

-0.37

projects

-0.36

)|^{

-0.36

ק

-0.36

 compliments

-0.35

 Audiodateien

-0.35

EFI

-0.35

 Giovan

-0.35

POSITIVE LOGITS

 users

0.68

 user

0.67

 gebruikers

0.60

的用户

0.59

 Users

0.59

 uživ

0.59

jspb

0.58

用戶

0.58

 USERS

0.57

 kullanıcı

0.57

Activations Density 0.437%

references to online platforms and user behavior in digital environments

users or user experience

their user

No Comments

No Known Activations