INDEX

Explanations

references to data types and biological terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 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

Jeografia

-0.46

 nahilalakip

-0.44

 planificación

-0.44

 propOrder

-0.43

 punggung

-0.43

Referències

-0.42

 infraestructura

-0.37

 fotografico

-0.37

 aproximado

-0.36

Tikang

-0.36

POSITIVE LOGITS

ata

0.84

ATA

0.78

stu

0.71

Stu

0.66

Stu

0.65

="@+

0.63

 Chamber

0.61

Chamber

0.61

 sentiment

0.60

Ace

0.59

Activations Density 0.787%

references to data types and biological terminology

No Comments

No Known Activations