INDEX

Explanations

specific quantifiable measurements or evaluations in a scientific context

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

LookAnd

-0.66

PMailer

-0.57

MLLoader

-0.54

 تعدى

-0.51

 Meksiku

-0.48

writeFieldEnd

-0.46

loit

-0.45

"%"

-0.44

Obrázky

-0.44

 intemper

-0.43

POSITIVE LOGITS

 empty

1.48

 absence

1.41

 zero

1.41

 blank

1.34

empty

1.23

 Absence

1.23

 silence

1.22

absence

1.21

 отсут

1.21

 inactive

1.20

Activations Density 2.073%

specific quantifiable measurements or evaluations in a scientific context

No Comments

No Known Activations