INDEX

Explanations

terms and concepts related to healthcare, genetic information, and property accessors

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

date, time, or administration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 JpaRepository

-0.86

WaitGroup

-0.81

 nakalista

-0.77

awtextra

-0.70

setVerticalGroup

-0.69

 utafitiHapana

-0.68

httphttps

-0.67

RTSN

-0.64

ंदीखरीदारी

-0.63

TagMode

-0.63

POSITIVE LOGITS

 judicia

0.38

 biais

0.38

 therapy

0.37

 affaires

0.37

 cuota

0.36

 conducta

0.35

 Nowak

0.35

 disease

0.34

eradish

0.33

Activations Density 0.064%

terms and concepts related to healthcare, genetic information, and property accessors

date, time, or administration

No Comments

No Known Activations