INDEX

Explanations

keywords related to legal documents and processes

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

past actions followed by prepositions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 kasarigan

-0.50

__(/*!

-0.49

WillAppear

-0.49

heses

-0.46

UserScript

-0.43

 goederen

-0.43

addPreferredGap

-0.43

insics

-0.42

usepackage

-0.42

 illustrationer

-0.42

POSITIVE LOGITS

 '\\;'

0.43

AccessorTable

0.39

getActiveSheet

0.39

 яке

0.39

 которое

0.38

ThroughAttribute

0.37

pictured

0.37

Географиясе

0.37

 което

0.37

transQ

0.37

Activations Density 0.125%

keywords related to legal documents and processes

past actions followed by prepositions

No Comments

No Known Activations