INDEX

Explanations

references to legal documentation and sections within legal texts

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

"of" followed by lawsuit terms or algorithm steps

np_acts-logits-general · gemini-2.0-flash

counts of complaints and algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Houſe

-0.64

 betweenstory

-0.61

 houſe

-0.59

 Theſe

-0.57

ContentAlignment

-0.57

ſſung

-0.54

 ſte

-0.51

 ſtate

-0.48

ädie

-0.48

 メンテナ

-0.48

POSITIVE LOGITS

tagext

0.41

ByExample

0.39

 Савезне

0.37

ensement

0.35

 nicio

0.35

 namorados

0.35

 jūsų

0.35

pegno

0.35

typeorm

0.34

/*!

0.34

Activations Density 0.754%

references to legal documentation and sections within legal texts

"of" followed by lawsuit terms or algorithm steps

counts of complaints and algorithms

No Comments

No Known Activations