INDEX

Explanations

terms related to retroactive applications and legal interpretations

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

Past/retroactive application

np_acts-logits-general · gemini-2.0-flash

apply retroactively

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

Efq

-0.69

tagHelperRunner

-0.68

 ISNI

-0.65

DotNetBar

-0.57

getMenuInflater

-0.55

#+#

-0.54

cyjna

-0.54

tdessen

-0.53

Obrázky

-0.53

 autorytatywna

-0.53

POSITIVE LOGITS

 past

1.43

過去の

1.24

 Past

1.24

Past

1.20

 previous

1.20

past

1.20

 historical

1.19

 older

1.17

old

1.17

 history

1.15

Activations Density 0.684%

terms related to retroactive applications and legal interpretations

Past/retroactive application

apply retroactively

No Comments

No Known Activations