INDEX

Explanations

specific nouns and terms associated with various objects and materials

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

Uncommon word beginnings

np_acts-logits-general · gemini-2.0-flash

word beginnings

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

accharides

-0.58

 relevant

-0.54

 global

-0.54

 inoxydable

-0.53

actose

-0.53

 maduro

-0.50

öffel

-0.49

 most

-0.49

 précis

-0.49

 concreta

-0.49

POSITIVE LOGITS

 disambiguazione

0.73

πάρχ

0.65

'<?

0.64

PreferredItem

0.63

Aholisi

0.61

 queſta

0.60

RenderAtEndOf

0.58

AntiForgeryToken

0.58

 betweenstory

0.58

 виправивши

0.57

Activations Density 0.279%

specific nouns and terms associated with various objects and materials

Uncommon word beginnings

word beginnings

No Comments

No Known Activations