INDEX

Explanations

questions and prompts related to user actions or choices

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

Question answering or prompts

np_acts-logits-general · gemini-2.0-flash

your questions

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

Personendaten

-0.61

 surla

-0.51

GOTREF

-0.50

AppMethodBeat

-0.49

 يتيمه

-0.48

 AttributeSet

-0.48

CloseOperation

-0.46

 ویکی‌پدی

-0.46

Географиясе

-0.46

 defStyleAttr

-0.45

POSITIVE LOGITS

 conmigo

0.42

 comigo

0.40

migrationBuilder

0.35

 adiós

0.35

PreferredItem

0.35

 mourut

0.35

EndGlobal

0.35

 encuentre

0.34

erapeutics

0.33

 возрасте

0.33

Activations Density 0.977%

questions and prompts related to user actions or choices

Question answering or prompts

your questions

No Comments

No Known Activations