INDEX

Explanations

terms related to technical specifications and metrics in various fields, such as computing and health

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

ArgsConstructor

-0.56

rillation

-0.54

 interlocutor

-0.52

MemoryWarning

-0.52

 aneurysm

-0.51

ocytosis

-0.51

vensis

-0.50

 estimés

-0.50

portál

-0.49

imerick

-0.48

POSITIVE LOGITS

 kaarangay

0.74

تقاوى

0.69

UnusedPrivate

0.67

Портали

0.57

 تضيفلها

0.57

httphttps

0.56

setViewportView

0.55

ఔ

0.54

 muualla

0.53

⁡

0.53

Activations Density 0.376%

terms related to technical specifications and metrics in various fields, such as computing and health

No Comments

No Known Activations