INDEX

Explanations

sections of code or documentation related to licensing or project information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 vitro

-1.19

PerformLayout

-1.01

 vivo

-0.96

expandindo

-0.89

 تضيفلها

-0.84

 NgModule

-0.73

 contextLoads

-0.73

 Vitro

-0.72

principalColumn

-0.71

 enfans

-0.71

POSITIVE LOGITS

bootstrapcdn

0.57

 sustained

0.54

 Cataluña

0.49

abspath

0.49

Uncle

0.46

bli

0.46

 Toma

0.46

TextBox

0.46

 berupa

0.45

odenal

0.45

Activations Density 0.061%

sections of code or documentation related to licensing or project information

No Comments

No Known Activations