INDEX

Explanations

terms related to damage or defects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

eradish

-0.57

 fusca

-0.55

ArrowToggle

-0.54

AntiForgeryToken

-0.52

 désigner

-0.52

 personalizados

-0.52

 betweenstory

-0.51

 élevés

-0.50

 MenuView

-0.49

 steigt

-0.49

POSITIVE LOGITS

 broken

1.48

broken

1.35

 Broken

1.31

Broken

1.24

 fractured

0.89

 damaged

0.84

impression

0.83

 Damaged

0.80

 يتيمه

0.76

 shattered

0.76

Activations Density 0.089%

terms related to damage or defects

No Comments

No Known Activations