INDEX

Explanations

references to protocols, acknowledgments, and methods in scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 متعلقه

-0.59

Diweddarwch

-0.57

rungsseite

-0.56

 المعيارى

-0.55

\{\\

-0.51

WebServlet

-0.48

ThroughAttribute

-0.44

webElementGuid

-0.43

 betweenstory

-0.41

POSITIVE LOGITS

 ModelExpression

0.91

ագրություններ

0.91

原始内容存档于

0.90

IBOutlet

0.81

 AssemblyProduct

0.79

 AttributeSet

0.75

principalColumn

0.70

GEBURTS

0.69

 Baillargeon

0.69

LEncoder

0.68

Activations Density 1.188%

references to protocols, acknowledgments, and methods in scientific research

No Comments

No Known Activations