INDEX

Explanations

words related to research papers about neural networks and data analysis

oai_token-act-pair · gemini-2.0-flash

statistical measurements

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Personendaten

-1.09

évaluateur

-1.08

HomeAsUpEnabled

-0.91

 InputDecoration

-0.87

RenderAtEndOf

-0.84

 EconPapers

-0.84

SBATCH

-0.83

 pinulongan

-0.83

 للمعارف

-0.83

Datuak

-0.83

POSITIVE LOGITS

0.43

ю

0.42

li

0.42

to

0.41

is

0.41

 that

0.41

om

0.40

re

0.38

0.37

and

0.37

Activations Density 6.647%

words related to research papers about neural networks and data analysis

statistical measurements

No Comments

No Known Activations