INDEX

Explanations

mentions of the name "Nelson."

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

Tokens followed by last names

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

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

deutig

-0.47

Diweddarwch

-0.44

__':

-0.41

 spagnolo

-0.40

__":

-0.40

ChildScrollView

-0.39

DockStyle

-0.39

govina

-0.39

Einzelnachweise

-0.38

useState

-0.36

POSITIVE LOGITS

webElementXpaths

0.62

 resourceCulture

0.54

 kaarangay

0.49

alisation

0.48

elson

0.47

ian

0.47

asson

0.46

inson

0.46

alities

0.45

ians

0.45

Activations Density 0.103%

mentions of the name "Nelson."

Tokens followed by last names

No Comments

No Known Activations