INDEX

Explanations

introductory phrases that signal the beginning of a new discussion or concept

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

demonstrating good oral

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 disambiguazione

-0.97

 الرياضيه

-0.92

rungsseite

-0.89

Viitteet

-0.88

httphttps

-0.87

RTSC

-0.85

قایناقلار

-0.85

jface

-0.82

évaluateur

-0.82

 صوتيه

-0.81

POSITIVE LOGITS

0.48

ธ์

0.43

Datuak

0.43

<em>

0.42

 solamente

0.41

 Fußballspieler

0.40

 tudi

0.40

 Namely

0.39

なんと

0.39

ませんでした

0.39

Activations Density 0.265%

introductory phrases that signal the beginning of a new discussion or concept

demonstrating good oral

No Comments

No Known Activations