INDEX

Explanations

technical terms and coding elements

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

énéral

-0.36

versiti

-0.35

 form

-0.32

 contributes

-0.32

łka

-0.31

↵

-0.29

cal

-0.29

-0.28

łki

-0.28

вают

-0.28

POSITIVE LOGITS

6.94

uxxxx

1.16

 EconPapers

1.09

 surla

1.07

httphttps

1.07

expandindo

1.02

WithIOException

1.01

Personensuche

0.99

 autorytatywna

0.97

 noDo

0.97

Activations Density 0.003%

technical terms and coding elements

No Comments

No Known Activations