INDEX

Explanations

numbers and technical specifications relevant to data and devices

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

BRI

-0.45

 $(\%)$

-0.44

 Ganz

-0.43

ത്ത

-0.42

 BoxDecoration

-0.42

łku

-0.41

écran

-0.41

ionario

-0.41

LoginComponent

-0.41

 usual

-0.41

POSITIVE LOGITS

 nahilalakip

0.68

ByVersion

0.68

DeleteBehavior

0.67

 ExecuteAsync

0.67

kháu

0.66

AntiForgeryToken

0.64

 متحده

0.64

 Exacts

0.63

 oprot

0.61

 externi

0.60

Activations Density 0.689%

numbers and technical specifications relevant to data and devices

No Comments

No Known Activations