INDEX

Explanations

terms related to neglect and its various forms

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

neglect

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

 AssemblyCompany

-0.54

Clik

-0.54

miller

-0.53

webElement

-0.53

Personendaten

-0.50

 ChromeDriver

-0.49

XmlAccessorType

-0.48

 informée

-0.48

versiti

-0.47

########.

-0.47

POSITIVE LOGITS

glected

1.10

 Neglect

1.02

 neglect

0.96

 neglected

0.88

 neglecting

0.85

 néglig

0.82

 descu

0.66

 Forget

0.64

 negligence

0.55

 abandono

0.54

Activations Density 0.008%

terms related to neglect and its various forms

neglect

No Comments

No Known Activations