INDEX

Explanations

medical and programming terminology

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

verwijspagina

-0.55

Personendaten

-0.54

 sula

-0.52

ernalia

-0.51

Abitanti

-0.51

 EconPapers

-0.50

ONAUT

-0.50

 '\\;'

-0.50

 оригіналу

-0.49

 MEMORIAL

-0.48

POSITIVE LOGITS

出版年

0.84

ton

0.83

TON

0.77

reactstrap

0.71

 nargin

0.68

BRO

0.64

bro

0.63

Bro

0.63

bro

0.62

ResponseEntity

0.60

Activations Density 2.664%

medical and programming terminology

No Comments

No Known Activations