INDEX

Explanations

topics related to human authority and belief systems

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

Questions or uncertainty

np_acts-logits-general · gemini-2.0-flash

Digital Twins, algebras, claims

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.94

Geplaatst

-0.77

 jScrollPane

-0.73

 peines

-0.69

phazard

-0.65

GEBURTSDATUM

-0.64

 engraçadas

-0.64

 cœurs

-0.64

RunWith

-0.64

 ***!

-0.63

POSITIVE LOGITS

 very

0.63

 still

0.60

UserScript

0.59

not

0.57

 quite

0.57

 highly

0.57

 something

0.56

 more

0.56

 really

0.56

 extremely

0.55

Activations Density 0.366%

topics related to human authority and belief systems

Questions or uncertainty

Digital Twins, algebras, claims

No Comments

No Known Activations