INDEX

Explanations

proper nouns associated with religious or political figures or institutions

oai_token-act-pair · gemini-2.0-flash

Pope

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

elemField

-0.93

出版年

-0.84

DebuggerNonUser

-0.84

 Houſe

-0.80

styleType

-0.75

 cherchés

-0.74

 myſelf

-0.71

afficheront

-0.69

tagHelperRunner

-0.68

Eſ

-0.68

POSITIVE LOGITS

↵

0.45

 like

0.45

lla

0.44

 getItemCount

0.43

like

0.43

avadoc

0.43

บาล

0.42

 Normdatei

0.42

 Picchu

0.40

 cardin

0.40

Activations Density 0.584%

proper nouns associated with religious or political figures or institutions

Pope

No Comments

No Known Activations