INDEX

Explanations

references to medical or biological terminology related to viruses and their interactions

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

Scientific publications and identifiers

np_acts-logits-general · gemini-2.0-flash

scientific and academic citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

 دیکھیے

-0.57

󠁴

-0.52

IsMutable

-0.50

Havolalar

-0.50

 Italijani

-0.49

KommentareTeilen

-0.47

 informée

-0.45

 Numerade

-0.44

पया

-0.43

 հղումներ

-0.42

POSITIVE LOGITS

 ARXIV

0.55

ORCID

0.54

 arXiv

0.49

 CRISPR

0.49

 https

0.48

令和

0.46

nullptr

0.46

 argparse

0.45

StandardCharsets

0.44

 Nachhaltigkeit

0.44

Activations Density 1.284%

references to medical or biological terminology related to viruses and their interactions

Scientific publications and identifiers

scientific and academic citations

No Comments

No Known Activations