INDEX

Explanations

geographic locations and associated entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Himo

-1.04

%)$

-0.76

ContextCompat

-0.70

 Janeiro

-0.69

<?

-0.68



-0.68

WAUKEE

-0.67

 Ανακτήθηκε

-0.67

 ExecuteAsync

-0.67

scrollY

-0.65

POSITIVE LOGITS

 VEGAS

0.86

 Vegas

0.74

Las

0.73

 Borno

0.71

 Ogun

0.70

Nevada

0.69

NEV

0.68

 vegas

0.68

 Valley

0.68

 Nevada

0.67

Activations Density 0.860%

geographic locations and associated entities

No Comments

No Known Activations