INDEX

Explanations

concepts related to artificial intelligence and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 LoggerFactory

-0.57

atoga

-0.52

 inefficiency

-0.47

Recovered

-0.47

getSupport

-0.47

vár

-0.46

 BRAND

-0.45

 inefficient

-0.45

prechung

-0.44

 Performer

-0.44

POSITIVE LOGITS

 ethical

0.79

 ethics

0.72

 Ethics

0.70

 Ethical

0.65

 unintended

0.63

UserScript

0.63

 ethically

0.61

Ethical

0.61

ethics

0.59

Ethics

0.59

Activations Density 0.382%

concepts related to artificial intelligence and its implications

No Comments

No Known Activations