INDEX

Explanations

instances of the word "smart" and its derivatives

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

"smart"

np_acts-logits-general · gemini-2.0-flash

smart followed by word

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-1.28

 resourceCulture

-0.97

 المعيارى

-0.90

yntaxException

-0.86

PreferredItem

-0.85

 CreateTagHelper

-0.78

 ostavi

-0.77

WriteTagHelper

-0.76

 Walkover

-0.76

bewerken

-0.75

POSITIVE LOGITS

 Smart

0.83

 smart

0.80

Smart

0.72

 SMART

0.71

smar

0.68

 Smar

0.67

SMART

0.67

smart

0.63

 intelligent

0.60

 smarter

0.59

Activations Density 0.037%

instances of the word "smart" and its derivatives

"smart"

smart followed by word

No Comments

No Known Activations