INDEX

Explanations

references to citations and bibliographic formatting

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

Superscripted symbols (e.g. numbers, daggers)

np_acts-logits-general · gemini-2.0-flash

academic formatting and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

PreExecute

-0.45

WireFormatLite

-0.38

 expectation

-0.38

DMETHOD

-0.37

原始内容存档于

-0.37

 Wicidata

-0.35

 deuda

-0.35

dafx

-0.35

 tryck

-0.34

 Himo

-0.34

POSITIVE LOGITS

eleste

0.52

 ✭✭

0.47

astéro

0.47

сей

0.45

máquina

0.44

 Cutler

0.43

 ब्रेकडाउन

0.42

énario

0.41

withOpacity

0.41

Roe

0.40

Activations Density 0.485%

references to citations and bibliographic formatting

Superscripted symbols (e.g. numbers, daggers)

academic formatting and symbols

No Comments

No Known Activations