INDEX

Explanations

terms related to regulation and regulatory frameworks

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

Tokens starting with "Reg" often followed by letters

np_acts-logits-general · gemini-2.0-flash

prefix "reg"

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

:✨

-0.69

Personensuche

-0.66

 للمعارف

-0.64

ItemBackground

-0.62

twimg

-0.62

 <>",

-0.59

تقاوى

-0.58

execSQL

-0.58

 تضيفلها

-0.58

 nonatomic

-0.57

POSITIVE LOGITS

REG

0.79

regs

0.63

 aveug

0.61

IntentFilter

0.61

 fermés

0.60

postsleuth

0.60

ული

0.57

REG

0.56

★★★★

0.55

PhysRev

0.55

Activations Density 0.141%

terms related to regulation and regulatory frameworks

Tokens starting with "Reg" often followed by letters

prefix "reg"

No Comments

No Known Activations