INDEX

Explanations

personal names and surnames

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 referrerpolicy

-0.36

WindowConstants

-0.32

 autorytatywna

-0.30

usercontent

-0.30

mybatisplus

-0.29

出版年

-0.29

ali

-0.27

Verwaltung

-0.26

 می‌

-0.26

 Chwiliwch

-0.25

POSITIVE LOGITS

 beſte

0.66

niſſe

0.65

ſicht

0.65

ſammen

0.63

 Waſſer

0.62

 Menſchen

0.61

оргаш

0.61

 ſont

0.61

<unused28>

0.60

<unused74>

0.60

Activations Density 0.852%

personal names and surnames

No Comments

No Known Activations