INDEX

Explanations

names and their meanings, particularly focusing on Hawaiian and other cultural names

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

or phrases defining a term's meaning

np_acts-logits-general · gemini-2.0-flash

word meaning or derivation

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

 defaultstate

-0.69

Viitteet

-0.62

calipsis

-0.56

لينكات

-0.55

Linki

-0.53

 createState

-0.50

claimers

-0.50

seteq

-0.49

Nationalité

-0.49

 الحره

-0.48

POSITIVE LOGITS

 meaning

1.04

 literally

0.90

 translated

0.88

 Literally

0.87

meaning

0.86

 derived

0.84

 translates

0.84

literally

0.83

derived

0.80

 literalmente

0.79

Activations Density 0.178%

names and their meanings, particularly focusing on Hawaiian and other cultural names

or phrases defining a term's meaning

word meaning or derivation

No Comments

No Known Activations