INDEX

Explanations

phrases related to legal definitions and regulations

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

Legal or formal language: "shall," "subsection."

np_acts-logits-general · gemini-2.0-flash

shall statements

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

 lenker

-0.77

ThroughAttribute

-0.61

oredCriteria

-0.58

 rund

-0.56

vs

-0.56

jooq

-0.56

faz

-0.56

 nahilalakip

-0.53

拜

-0.51

~$

-0.51

POSITIVE LOGITS

 shall

1.08

shall

1.02

 Shall

0.85

 avoient

0.69

 prêtres

0.69

 vérit

0.68

 dignité

0.68

Shall

0.68

 ſhall

0.67

 auroit

0.67

Activations Density 0.799%

phrases related to legal definitions and regulations

Legal or formal language: "shall," "subsection."

shall statements

No Comments

No Known Activations