INDEX

Explanations

references to the concept of "hard work."

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

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

 propOrder

-0.88

abestanden

-0.80

 BoxFit

-0.79

ollectionView

-0.78

IndentedString

-0.72

 MonoBehaviour

-0.69

 ویکی‌پدیا

-0.69

 InputDecoration

-0.68

 spesa

-0.67

 Италијани

-0.67

POSITIVE LOGITS

 hard

1.42

 Hard

1.37

 HARD

1.30

Hard

1.27

HARD

1.23

hard

1.21

 harder

1.01

 hardest

0.96

硬

0.94

 hards

0.92

Activations Density 0.050%

references to the concept of "hard work."

No Comments

No Known Activations