INDEX

Explanations

legal definitions and formal definitions of terms

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

the word "definition"

np_acts-logits-general · gemini-2.0-flash

definition of X

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.51

afficheront

-0.48

AndroidJUnit

-0.47

 հղումներ

-0.46

Datuak

-0.44

зулта

-0.43

 mostrarán

-0.42

XtraReports

-0.42

BASEPATH

-0.40

SBATCH

-0.40

POSITIVE LOGITS

 definition

2.67

 definitions

2.33

 Definition

2.20

definition

2.17

 definición

2.13

 definição

2.06

 définition

2.05

Definition

2.03

 Definitions

1.97

定義

1.87

Activations Density 0.707%

legal definitions and formal definitions of terms

the word "definition"

definition of X

No Comments

No Known Activations