INDEX

Explanations

words related to art installations and performances

oai_token-act-pair · gemini-2.0-flash

installation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 track

-0.44

━━━

-0.42

э

-0.41

 doing

-0.40

he

-0.40

]);

-0.40

asting

-0.38

bic

-0.38

ieren

-0.37

cogni

-0.37

POSITIVE LOGITS

ContentAsync

1.04

 utafitiHapana

0.90

 المعيارى

0.89

 ويكيپيديا

0.79

 useAppContext

0.72

 ferroviaire

0.71

DockStyle

0.70

Datuak

0.70

ReusableCell

0.70

 ویکی‌پدیا

0.69

Activations Density 1.011%

words related to art installations and performances

installation

No Comments

No Known Activations