INDEX

Explanations

occurrences of the letter 'n'

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

"n" followed by a consonant

np_acts-logits-general · gemini-2.0-flash

n + suffix forming words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

RenderAtEndOf

-0.77

archiviato

-0.73

 gynhyrchwyd

-0.69

 дописавши

-0.68

webElementXpaths

-0.66

 Normdatei

-0.66

Демографія

-0.65

 nahilalakip

-0.64

Referències

-0.63

TabIndex

-0.59

POSITIVE LOGITS

ionView

0.48

oubliez

0.48

اعدة

0.42

digo

0.40

sync

0.40

utí

0.39

 spacy

0.39

arnia

0.39

olan

0.39

 fundo

0.38

Activations Density 0.199%

occurrences of the letter 'n'

"n" followed by a consonant

n + suffix forming words

No Comments

No Known Activations