INDEX

Explanations

words associated with organized events happening at a certain time or location

oai_token-act-pair · gemini-2.0-flash

events

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 متعلقه

-0.69

بوابة

-0.60

#+#

-0.58

PAIGN

-0.55

 Gara

-0.54

Mag

-0.49

 kron

-0.48

ipedi

-0.48

PhysRev

-0.47

POSITIVE LOGITS

IntoConstraints

1.18

HtmlAttribute

0.69

DockStyle

0.66

didSet

0.65

onActivityResult

0.60

 pinulongan

0.59

SequentialGroup

0.58

Tikang

0.54

 Réponses

0.53

endphp

0.51

Activations Density 10.094%

words associated with organized events happening at a certain time or location

events

No Comments

No Known Activations