INDEX

Explanations

phrases related to examination or analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

🔥🔥

-0.60

bitat

-0.58

 hossz

-0.58

 Roderick

-0.58

feuer

-0.56

 uitges

-0.55

 palavra

-0.55

cipar

-0.54

 Romero

-0.54

ารถ

-0.53

POSITIVE LOGITS

]$}

0.94

存于互联网档案馆

0.92

onViewCreated

0.91

ніципалі

0.87

 AspNetCore

0.87

 Administrativna

0.85

 disambiguazione

0.85

 VIEW

0.84

IUrlHelper

0.84

########.

0.81

Activations Density 0.098%

phrases related to examination or analysis

No Comments

No Known Activations