INDEX

Explanations

keywords related to scientific terms and classifications

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

Two or three letter codes

np_acts-logits-general · gemini-2.0-flash

abbreviations and codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.52

躇

-0.45

 ویکی‌پدی

-0.41

 समीक्षाओं

-0.40

MLElement

-0.39

thre

-0.39

منت

-0.39

 Willi

-0.38

vincent

-0.38

 autorytatywna

-0.37

POSITIVE LOGITS

 cadeia

0.66

 maș

0.65

fastjson

0.58

Kaieteur

0.58

vaadin

0.58

hány

0.58

 cappuccio

0.57

carat

0.56

Sas

0.56

ajar

0.55

Activations Density 1.984%

keywords related to scientific terms and classifications

Two or three letter codes

abbreviations and codes

No Comments

No Known Activations