INDEX

Explanations

terms and concepts related to perturbative expansions and their applications in quantum physics

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

perturbative expansions

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

 estekak

-0.48

 Normdatei

-0.48

 MatDialog

-0.45

 mourut

-0.44

IBarButtonItem

-0.42

XtraBars

-0.41

SceneManagement

-0.41

émie

-0.40

 AssemblyVersion

-0.40

ValueStyle

-0.40

POSITIVE LOGITS

 perturbation

0.44

substack

0.40

 slow

0.39

parsedMessage

0.38

 dominante

0.38

canActivate

0.37

DebuggerNonUser

0.35

anglès

0.35

 scarring

0.35

 analysis

0.34

Activations Density 0.109%

terms and concepts related to perturbative expansions and their applications in quantum physics

perturbative expansions

No Comments

No Known Activations