INDEX

Explanations

medical terminology related to health and treatment methods

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

mathematical expressions and code

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 Paglinawan

-0.53

GOTREF

-0.48

 disponibilités

-0.44

 TextInputType

-0.40

AndEndTag

-0.40

 wuß

-0.38

 للمعارف

-0.37

mybatisplus

-0.36

yonel

-0.36

 DbSet

-0.35

POSITIVE LOGITS

Попис

0.54

bootstrapcdn

0.52

 propOrder

0.51

+#+#

0.50

bình

0.44

 Meksiku

0.43

 vito

0.43

ifikationer

0.42

 ✭✭

0.42

KommentareTeilen

0.42

Activations Density 0.478%

medical terminology related to health and treatment methods

mathematical expressions and code

No Comments

No Known Activations