INDEX

Explanations

terms related to employment and employees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bootstrapcdn

-0.85

AxisAlignment

-0.83

jsdelivr

-0.82

execSQL

-0.81

Personendaten

-0.80

 defaultstate

-0.78

<!--[

-0.77

LEncoder

-0.75

 EconPapers

-0.74

Sut

-0.72

POSITIVE LOGITS

employees

0.69

Employees

0.65

 employees

0.63

LOYEES

0.62

 ansatte

0.57

employeeId

0.57

 dipendenti

0.52

 salari

0.52

employee

0.52

 Mullen

0.52

Activations Density 0.107%

terms related to employment and employees

No Comments

No Known Activations