INDEX

Explanations

geographical descriptions and measurements related to land areas and boundaries

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

area boundaries

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

Repository

-0.34

 regel

-0.34

 novelty

-0.33

 viral

-0.33

 nouve

-0.33

OfBirth

-0.33

Välislingid

-0.32

 Coruña

-0.32

 Ciencia

-0.32

 Sinclair

-0.32

POSITIVE LOGITS

IntoConstraints

0.58

DockStyle

0.57

 gräns

0.52

範圍

0.47

ConstraintMaker

0.46

 parishes

0.46

sidemargin

0.46

featureID

0.46

MigrationBuilder

0.46

 nakalista

0.45

Activations Density 0.037%

geographical descriptions and measurements related to land areas and boundaries

area boundaries

No Comments

No Known Activations