INDEX

Explanations

comparisons and unique features associated with digital tools and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Kela

-0.47

EMS

-0.40

GMP

-0.40

unist

-0.39

sem

-0.39

bum

-0.39

berge

-0.39

rap

-0.38

lock

-0.38

inz

-0.38

POSITIVE LOGITS

 disambiguazione

0.58

enumii

0.56

 transfieras

0.52

帖最后由

0.50

Билгалдахарш

0.48

 lateinit

0.46

 picioare

0.46

twimg

0.45

Cyfeiriadau

0.45

AndroidJUnit

0.45

Activations Density 0.661%

comparisons and unique features associated with digital tools and services

No Comments

No Known Activations