INDEX

Explanations

elements related to learning, instruction, and foundational knowledge in various contexts

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

"basic" or its translation

np_acts-logits-general · gemini-2.0-flash

basic concepts and fundamentals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adaptiveStyles

-0.42

expandindo

-0.41

 betweenstory

-0.38

inWeight

-0.34

@[+][

-0.34

リューション

-0.32

تقاوى

-0.32

évaluateur

-0.31

الإنجليزية

-0.30

reibe

-0.30

POSITIVE LOGITS

 basic

2.95

basic

2.69

 basics

2.58

Basic

2.52

 básico

2.45

 Basic

2.42

 básica

2.38

基本

2.27

 básicos

2.23

 básicas

2.14

Activations Density 0.448%

elements related to learning, instruction, and foundational knowledge in various contexts

"basic" or its translation

basic concepts and fundamentals

No Comments

No Known Activations