INDEX

Explanations

parameters related to web page resources or configurations

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

<start_of_turn> user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.67

 MainAxisSize

-0.65

 للاسماء

-0.63

TestingModule

-0.61

ніципалі

-0.58

ArgumentParser

-0.56

extAlignment

-0.55

queryInterface

-0.53

dafx

-0.51

ftagPool

-0.51

POSITIVE LOGITS

İstinadlar

0.36

ed

0.36

 Leslie

0.36

rev

0.31

refresh

0.30

 SINCE

0.30

 unicornio

0.30

 تعدى

0.30

 rotation

0.30

Населення

0.29

Activations Density 0.011%

parameters related to web page resources or configurations

<start_of_turn> user

No Comments

No Known Activations