INDEX

Explanations

terms related to employment and work processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 chi̍t

-0.68

 NgModule

-0.67

mobileqq

-0.65

 StringTokenizer

-0.65

Datuak

-0.63

TTS

-0.63

 Popov

-0.62

InstanceState

-0.61

 Moisturi

-0.61

 touristes

-0.60

POSITIVE LOGITS

 work

2.27

 Work

2.02

Work

1.95

work

1.92

 WORK

1.91

 working

1.76

WORK

1.74

working

1.64

Working

1.62

 Working

1.60

Activations Density 0.224%

terms related to employment and work processes

No Comments

No Known Activations