INDEX

Explanations

keywords related to legal cases and courtroom proceedings

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

followed by prepositions or articles

np_acts-logits-general · gemini-2.0-flash

legal cases and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 AssemblyCompany

-0.68

 <<<<<<<<<<<<<<

-0.63

verifyException

-0.62

 trebui

-0.60



-0.58

tiérrez

-0.57



-0.57

<unused49>

-0.57

Szy

-0.57

 geweſen

-0.57

POSITIVE LOGITS

extAlignment

0.41

ⓧ

0.39

 ✭✭

0.39

цезда

0.36

⁩

0.35

IUrlHelper

0.34

LikeLike

0.31

 Taktlose

0.31

 UITableViewCell

0.31

AISSEE

0.29

Activations Density 24.691%

keywords related to legal cases and courtroom proceedings

followed by prepositions or articles

legal cases and processes

No Comments

No Known Activations