INDEX

Explanations

terms related to legal and healthcare issues affecting individuals and families

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

Words/punctuation followed by prepositions

np_acts-logits-general · gemini-2.0-flash

legal or regulatory context

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

IntoConstraints

-0.64

NUMX

-0.62

jublj

-0.60

thâu

-0.58

 apologise

-0.58

 inspirations

-0.56

 framför

-0.56

 cherchés

-0.56

 resourceCulture

-0.55

 himo

-0.55

POSITIVE LOGITS

 legally

1.73

 legal

1.38

 légal

1.28

 laws

1.24

 legality

1.23

 regulations

1.19

legal

1.17

 lawfully

1.16

 federally

1.14

 legislation

1.12

Activations Density 0.593%

terms related to legal and healthcare issues affecting individuals and families

Words/punctuation followed by prepositions

legal or regulatory context

No Comments

No Known Activations