INDEX

Explanations

instances of the term "display" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 volontaire

-0.83

 rêver

-0.81

슷

-0.76

besar

-0.75

 fallu

-0.75

لينا

-0.74

 Zuma

-0.74

=>$

-0.73

 hâte

-0.71

 situés

-0.71

POSITIVE LOGITS

 DISPLAY

1.60

 displays

1.59

 display

1.58

 Displays

1.56

displays

1.54

 Display

1.50

Displays

1.50

display

1.34

DISPLAY

1.33

Display

1.32

Activations Density 0.044%

instances of the term "display" in various contexts

No Comments

No Known Activations