INDEX

Explanations

references to logos in various formats and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Controllo

-0.59

 AttributeSet

-0.57

moveToFirst

-0.56

cassandra

-0.56

 invokingState

-0.55

 createSlice

-0.55

subsection

-0.54

@"/

-0.54

üksek

-0.54

 Мексичка

-0.53

POSITIVE LOGITS

 logo

2.51

 Logo

2.37

logo

2.35

 logos

2.26

Logo

2.22

 LOGO

2.15

LOGO

1.87

 logotipo

1.78

logos

1.77

 Logos

1.73

Activations Density 0.092%

references to logos in various formats and contexts

No Comments

No Known Activations