INDEX

Explanations

numerical or coded information related to legal or regulatory documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 gesteld

-0.44

 etme

-0.39

⋙

-0.39

 Picchu

-0.39

ęku

-0.39

 nullptr

-0.38

 škol

-0.38

 girasol

-0.37

ulmuş

-0.37

laß

-0.37

POSITIVE LOGITS

はじめに

0.84

enumii

0.80

 تضيفلها

0.79

 betweenstory

0.75

 dAtA

0.71

 createState

0.71

fromnode

0.69

脚注の使い方

0.69

WebServlet

0.68

 TAMBÉM

0.68

Activations Density 0.590%

numerical or coded information related to legal or regulatory documents

No Comments

No Known Activations

numerical or coded information related to legal or regulatory documents

No Comments

No Known Activations