INDEX

Explanations

terms related to quantum systems and their thermodynamic properties

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

about systems

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

 tục

-0.35

 विश्वसनीयता

-0.35

 high

-0.33

leg

-0.31

 capital

-0.31

 measure

-0.30

 distribution

-0.30

 difference

-0.30

 maksi

-0.29

 condition

-0.29

POSITIVE LOGITS

 مشين

0.93

RenderAtEndOf

0.63

 snippetHide

0.62

ReusableCell

0.60

IVEREF

0.60

 esternos

0.59

arangay

0.59

cussed

0.55

XtraReports

0.55

 Wiktionnaire

0.55

Activations Density 0.348%

terms related to quantum systems and their thermodynamic properties

about systems

No Comments

No Known Activations