INDEX

Explanations

frequency of certain phrases or keywords related to digital interactions or transactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 typelib

-0.46

лтемелер

-0.44

blurRadius

-0.41

Rptr

-0.40

 protoimpl

-0.39

TargetApi

-0.39

RegistryLite

-0.39

CDCl

-0.38

DataPropertyName

-0.38

WriteTagHelper

-0.38

POSITIVE LOGITS

 незавершена

0.51

fromnode

0.50

 kasarigan

0.47

úgó

0.46

 AssemblyCulture

0.45

 Италијани

0.44

oa̍t

0.43

AnimationsModule

0.41

imente

0.40

ParallelGroup

0.38

Activations Density 1.162%

frequency of certain phrases or keywords related to digital interactions or transactions

No Comments

No Known Activations