INDEX

Explanations

credits or authorship information in a document

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

Code comments with "@author"

np_acts-logits-general · gemini-2.0-flash

author names

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

deviantart

-0.51

πάρχ

-0.45

 once

-0.45

 indisponible

-0.43

getDoctrine

-0.43

initializeApp

-0.43

 bali

-0.42

 schemes

-0.42

DOI

-0.42

complexType

-0.41

POSITIVE LOGITS

 nahilalakip

0.87

 يتيمه

0.86

 Италијани

0.86

 Савезне

0.85

complexContent

0.78

expandindo

0.73

MigrationBuilder

0.72

帖最后由

0.72

 culturelle

0.72

Personensuche

0.71

Activations Density 0.029%

credits or authorship information in a document

Code comments with "@author"

author names

No Comments

No Known Activations