INDEX

Explanations

instances of the word "draw" and its variations, indicating a focus on actions related to drawing or attracting attention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 antemano

-0.68

EndProject

-0.67

 ambientales

-0.66

 Schulte

-0.64

IsContent

-0.64

/**

-0.63

globalData

-0.61

️

-0.61

 inoxydable

-0.59

poved

-0.58

POSITIVE LOGITS

 drawn

1.71

 Drawn

1.52

 Draws

1.48

 draw

1.47

 draws

1.46

 drew

1.45

 drawing

1.44

drawn

1.42

 Draw

1.37

Drawn

1.35

Activations Density 0.081%

instances of the word "draw" and its variations, indicating a focus on actions related to drawing or attracting attention

No Comments

No Known Activations