INDEX

Explanations

words related to specific scientific or technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ValueStyle

-0.84

 cherchés

-0.83

 كومونز

-0.75

 سكانية

-0.72

tagext

-0.70

 Tite

-0.68

AccessorTable

-0.68

+#+#

-0.68

Nö

-0.67

Sö

-0.65

POSITIVE LOGITS

 Polish

0.65

 поль

0.64

 Pologne

0.62

Polish

0.60

 Poland

0.60

 Kowalski

0.60

 Поль

0.58

 Polen

0.58

 Lewandowski

0.58

 Nowak

0.57

Activations Density 0.193%

words related to specific scientific or technical terms

No Comments

No Known Activations