INDEX

Explanations

references to specific companies and brands

oai_token-act-pair · gpt-4o-mini Triggered by @bot

starting with "Bio" or single letters

np_acts-logits-general · gemini-2.0-flash

initialisms and compound words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 بيها

-0.58

principalColumn

-0.53

JsonHelper

-0.52

 textStatus

-0.52

Demikian

-0.52

GEBURTSDATUM

-0.49

 ảo

-0.49

hingga

-0.49

GridColumn

-0.48

DropColumn

-0.47

POSITIVE LOGITS

IonicModule

0.63

 betweenstory

0.57

 organizers

0.53

########.

0.53

 Audiodateien

0.52

 يتيمه

0.51

 staffers

0.51

 oprot

0.51

펴

0.49

 calyx

0.49

Activations Density 0.186%

references to specific companies and brands

starting with "Bio" or single letters

initialisms and compound words

No Comments

No Known Activations