INDEX

Explanations

mathematical terms and expressions related to models and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ASIA

-0.43

kev

-0.42

 romantic

-0.41

 compri

-0.39

Ри

-0.38

igg

-0.38

romantic

-0.38

тек

-0.37

vla

-0.37

Kjelder

-0.37

POSITIVE LOGITS

 controller

0.94

 controllers

0.87

 Controller

0.85

StoryboardSegue

0.82

 initComponents

0.80

 Controllers

0.80

 control

0.76

 Kalman

0.75

 controladores

0.74

 controlador

0.73

Activations Density 0.484%

mathematical terms and expressions related to models and functions

No Comments

No Known Activations