INDEX

Explanations

coding terminology related to file handling and content types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

áctenos

-0.39

heça

-0.33

endimiento

-0.32

 سد

-0.32

 AutoMapper

-0.31

ผล

-0.31

 Jensen

-0.31

 autorité

-0.30

 TMPro

-0.30

 Leistung

-0.29

POSITIVE LOGITS

contentLoaded

0.68

 estekak

0.57

WebServlet

0.51

protoimpl

0.49

 informée

0.48

 calendriers

0.47

baix

0.47

Chham

0.46

romolecules

0.45

 Puro

0.45

Activations Density 0.339%

coding terminology related to file handling and content types

No Comments

No Known Activations