INDEX

Explanations

code snippets related to machine learning models

oai_token-act-pair · gemini-2.0-flash

Code and model loading

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UnitTesting

-0.54

 contextLoads

-0.54

+#+#

-0.52

 initComponents

-0.51

 directed

-0.49

Odkazy

-0.48

exitRule

-0.47

цкого

-0.46

{}{}

-0.46

 disambiguazione

-0.45

POSITIVE LOGITS

 GRATU

0.57

 remise

0.54

further

0.54

 himo

0.54

 Zier

0.53

ataires

0.53

ifornie

0.51

 Replay

0.51

oader

0.50

 ISRAEL

0.50

Activations Density 1.181%

code snippets related to machine learning models

Code and model loading

No Comments

No Known Activations