INDEX

Explanations

highly frequent proper nouns and names in a document

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

Hungarian language words/tokens

np_acts-logits-general · gemini-2.0-flash

Hungarian and place names

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

tű

-0.57

cektir

-0.52

Fordítás

-0.51

 kív

-0.51

 olvas

-0.51

 különböz

-0.50

 segíts

-0.47

 jegy

-0.47

 kereszt

-0.46

 tárgy

-0.45

POSITIVE LOGITS

Hozzáférés

0.86

 famí

0.82

 Himo

0.75

FieldBuilder

0.75

wpi

0.74

rungsseite

0.73

 disambiguazione

0.71

SuspendLayout

0.70

 GoogleFonts

0.69

TagMode

0.69

Activations Density 0.017%

highly frequent proper nouns and names in a document

Hungarian language words/tokens

Hungarian and place names

No Comments

No Known Activations