INDEX

Explanations

phrases and concepts related to monitoring and oversight in various contexts

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

 autorytatywna

-0.85

abestanden

-0.57

UpInside

-0.54

UPAC

-0.51

 thiệu

-0.50

PMailer

-0.48

 Preference

-0.47

дования

-0.46

 estoppel

-0.46

脚注の使い方

-0.45

POSITIVE LOGITS

 monitoring

2.62

 monitor

2.37

 Monitoring

2.34

 monitored

2.27

Monitoring

2.24

monitoring

2.14

 monitors

2.12

 Monitor

2.08

monitor

2.06

 MONITORING

1.98

Activations Density 0.453%

phrases and concepts related to monitoring and oversight in various contexts

No Comments

No Known Activations