INDEX

Explanations

references to authors and their contributions in academic papers

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

Abbreviations followed by periods

np_acts-logits-general · gemini-2.0-flash

initials and surnames

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 sää

-0.59

 primeiras

-0.55

 sentidos

-0.55

 miniaturka

-0.54

 kysy

-0.53

 väli

-0.53

colgante

-0.53

 adquis

-0.52

 primeras

-0.52

MigrationBuilder

-0.50

POSITIVE LOGITS

 defaultstate

0.62

WEBPACK

0.46

0.44

0.43

0.42

ๆ

0.42

LikeLike

0.41

0.39

0.37

Заключение

0.36

Activations Density 0.366%

references to authors and their contributions in academic papers

Abbreviations followed by periods

initials and surnames

No Comments

No Known Activations