INDEX

Explanations

mathematical terms and operations related to statistics and data processing

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

min/max values

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

 HasFactory

-0.44

tenths

-0.40

tensive

-0.38

 NSCoder

-0.37

endants

-0.37

iolis

-0.36

doma

-0.36

pernic

-0.35

mia

-0.35

 Metal

-0.35

POSITIVE LOGITS

 createState

0.64

addPreferredGap

0.62

VIAF

0.59

Kjelder

0.54

SharedCtor

0.49

PropertyChanging

0.49

awaiter

0.49

addContainerGap

0.48

 Мексичка

0.47

glMatrixMode

0.46

Activations Density 0.091%

mathematical terms and operations related to statistics and data processing

min/max values

No Comments

No Known Activations