INDEX

Explanations

scientific terminology and concepts related to neuroscience and biology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Gue

-0.43

($)

-0.42

 Sharpe

-0.42

 Forum

-0.42

PHPExcel

-0.41

 FormData

-0.40

ya

-0.40

Access

-0.40

leski

-0.39

 Star

-0.39

POSITIVE LOGITS

 مرئيه

0.89

 autorytatywna

0.85

日閲覧

0.73

awtextra

0.72

 jsPsych

0.71

tvguidetime

0.70

 arşivlendi

0.70

 lenker

0.69

onomía

0.69

 EconPapers

0.68

Activations Density 1.742%

scientific terminology and concepts related to neuroscience and biology

No Comments

No Known Activations