INDEX

Explanations

LaTeX commands related to document formatting and layout specifications

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

document layout commands

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

 ilustracja

-0.47

 médicaux

-0.46

 varones

-0.43

 fédé

-0.42

 Pflichten

-0.41

 ancianos

-0.39

 fiscales

-0.39

 cielos

-0.38

 huelga

-0.38

 laborales

-0.38

POSITIVE LOGITS

newcommand

1.67

 AssemblyTitle

0.73

 intptr

0.63

renewcommand

0.63

 AssemblyCulture

0.59

 abbreviations

0.57

findpost

0.54

cardname

0.54

 InputDecoration

0.54

chloric

0.54

Activations Density 0.001%

LaTeX commands related to document formatting and layout specifications

document layout commands

No Comments

No Known Activations