INDEX

Explanations

specific terms and their definitions or usages in various contexts

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

definition of a term

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

setVerticalGroup

-0.62

 NUKAT

-0.52

setupUi

-0.52

AndroidJUnit

-0.51

SBATCH

-0.49

majánló

-0.49

 JpaRepository

-0.47

borderFill

-0.47

ใส

-0.47

恹

-0.47

POSITIVE LOGITS

verwijspagina

0.48

 Administrativna

0.47

enumi

0.45

 phrase

0.42

ACHUSET

0.38

 term

0.37

(?:

0.37

 resourceCulture

0.35

Einzelnachweise

0.35

Activations Density 0.018%

specific terms and their definitions or usages in various contexts

definition of a term

No Comments

No Known Activations