INDEX

Explanations

mentions of the word 'New' associated with geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

GEBURTSDATUM

-1.38

 itſelf

-1.34

 nakalista

-1.24

 виправивши

-1.22

 disambiguazione

-1.19

 ComVisible

-1.17

 propOrder

-1.16

principalTable

-1.13

.*")]

-1.12

 ainfi

-1.11

POSITIVE LOGITS

New

1.95

New

1.67

NEW

0.91

NEW

0.89

 South

0.82

 न्यू

0.79

ew

0.77

NY

0.77

 Nueva

0.76

 North

0.76

Activations Density 0.047%

mentions of the word 'New' associated with geographical locations

No Comments

No Known Activations