INDEX

Explanations

words related to advertising and online content promotion

oai_token-act-pair · gemini-2.0-flash

content/posts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Демографія

-0.78

 sapon

-0.62

SharedDtor

-0.61

 gawas

-0.60

 Fasc

-0.58

RTLR

-0.58

 Dmit

-0.58

 estekak

-0.57

 surla

-0.57

abetes

-0.56

POSITIVE LOGITS

cius

0.49

 sharing

0.49

StoryboardSegue

0.48

moveToFirst

0.46

kat

0.46

WriteTagHelper

0.45

ersatz

0.45

Sharing

0.44

 shares

0.43

方で

0.43

Activations Density 8.323%

words related to advertising and online content promotion

content/posts

No Comments

No Known Activations