INDEX

Explanations

positive feedback and expressions of satisfaction about someone's work or performance

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

her books

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

رشف

-0.36

zium

-0.34

 fortun

-0.33

photobucket

-0.33

tokyo

-0.33

namics

-0.32

ereço

-0.32

beke

-0.32

pacs

-0.32

VYMaps

-0.31

POSITIVE LOGITS

XmlAccessorType

0.60

Datuak

0.59

 Majefty

0.58

providedIn

0.58

complexContent

0.52

berdayakan

0.52

ंदीखरीदारी

0.50

WriteLiteral

0.49

 Jefus

0.46

 disambiguazione

0.46

Activations Density 0.001%

positive feedback and expressions of satisfaction about someone's work or performance

her books

No Comments

No Known Activations