INDEX

Explanations

code-related terms and functions, especially those used in programming or LaTeX environments

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 filles

-0.39

ervlak

-0.35

 Ursache

-0.33

 ferons

-0.33

 sahi

-0.32

 pistes

-0.31

 たら

-0.31

 Polri

-0.30

 Umständen

-0.30

 flota

-0.30

POSITIVE LOGITS

newcommand

3.67

renewcommand

1.63

DeclareMath

1.27

newtheorem

1.24

 AssemblyTitle

0.94

providecommand

0.92

usepackage

0.88

Personendaten

0.85

 AssemblyCompany

0.76

 lateinit

0.73

Activations Density 0.055%

code-related terms and functions, especially those used in programming or LaTeX environments

No Comments

No Known Activations