INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Мексичка

-0.82

хьтан

-0.77

GEBURTSDATUM

-0.69

новништво

-0.68

 يتيمه

-0.67

 FetchType

-0.63

 otomatig

-0.63

*}[

-0.62

Personendaten

-0.60

:✨

-0.59

POSITIVE LOGITS

).

0.59

'.

0.58

etc

0.57

などなど

0.57

 semuanya

0.54

etc

0.54

.).

0.54

".

0.53

.)

0.51

Activations Density 0.221%

No Comments

No Known Activations