INDEX

Explanations

names of authors or contributors in scholarly contexts

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

people's names

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

DockStyle

-0.80

 AssemblyTitle

-0.79

 للمعارف

-0.72

contentLoaded

-0.68

="@+

-0.67

verwijspagina

-0.67

 MainAxisSize

-0.66

+#+#

-0.66

principalColumn

-0.65

‍♂️

-0.65

POSITIVE LOGITS

Obrigada

0.50

ค่ะ

0.37

0.35

 atsi

0.34

 Nava

0.33

 PLUS

0.33

0.32

navigateTo

0.32

속

0.31

Activations Density 0.059%

names of authors or contributors in scholarly contexts

people's names

No Comments

No Known Activations