INDEX

Explanations

numerical values and their relationships within specific contexts

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

numbers and limits

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

styleType

-0.43

AndPassword

-0.37

 operas

-0.36

rxjs

-0.34

 الأق

-0.32

IANGLES

-0.32

Edm

-0.31

 Technic

-0.31

 Ceremon

-0.30

setQuery

-0.30

POSITIVE LOGITS

AsUp

0.58

Personensuche

0.54

 ExecuteAsync

0.51

 getMax

0.51

 betweenstory

0.51

bouncycastle

0.50

 disambiguazione

0.50

Spoljašnje

0.48

 maksimal

0.47

 BaseEntity

0.47

Activations Density 0.077%

numerical values and their relationships within specific contexts

numbers and limits

No Comments

No Known Activations