INDEX

Explanations

phrases related to health and well-being

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

introduction and overview

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 noDo

-0.58

 समीक्षक

-0.51

MessageTagHelper

-0.49

تفصیلات

-0.49

XmlAccessType

-0.49

ंदीखरीदारी

-0.48

principalColumn

-0.47

HasAnnotation

-0.47

tagHelperRunner

-0.47

FieldBuilder

-0.45

POSITIVE LOGITS

 AppCompatTheme

0.42

 foundation

0.40

 history

0.40

 structure

0.40

 definition

0.38

 definitions

0.38

 introduction

0.38

 identification

0.36

 defines

0.36

overview

0.36

Activations Density 0.006%

phrases related to health and well-being

introduction and overview

No Comments

No Known Activations