INDEX

Explanations

references to logos and branding elements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 autorytatywna

-0.83

oa̍t

-0.72

scriptcase

-0.69

Jeografia

-0.68

 Fulton

-0.65

fjspx

-0.61

wijl

-0.60

 getItemCount

-0.60

 Мексичка

-0.59

ensement

-0.58

POSITIVE LOGITS

 logo

3.30

 Logo

3.01

logo

2.92

 logos

2.89

Logo

2.80

 LOGO

2.63

LOGO

2.31

 logotipo

2.18

logos

2.12

 Logos

2.09

Activations Density 0.046%

references to logos and branding elements

No Comments

No Known Activations