INDEX

Explanations

instances of numerical values or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

というわけで

-0.40

NewRow

-0.39

timents

-0.38

writeFieldEnd

-0.38

 ligiloj

-0.37

 odpowiada

-0.35

ordenadas

-0.35

TabIndex

-0.34

 kív

-0.34

enumi

-0.33

POSITIVE LOGITS

 autorytatywna

0.62

 nahilalakip

0.61

はじめに

0.57

 tslint

0.54

 calendriers

0.52

BindingResult

0.50

لينكات

0.50

Rujuakan

0.49

 albeit

0.49

Kjelder

0.48

Activations Density 0.870%

instances of numerical values or entities

No Comments

No Known Activations