INDEX

Explanations

terms related to selection and user interface interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

LayoutConstraint

-0.38

 güçlü

-0.35

MessageState

-0.32

eador

-0.31

mazing

-0.30

tipation

-0.29

ubernur

-0.29

istoitu

-0.29

 abundancia

-0.29

 Förder

-0.29

POSITIVE LOGITS

DIPSETTING

0.68

transQ

0.65

JMenuItem

0.62

 JMenuItem

0.61

JMenu

0.59

 opcion

0.59

MenuItem

0.58

 menu

0.57

 onOptions

0.57

 Menu

0.57

Activations Density 0.394%

terms related to selection and user interface interactions

No Comments

No Known Activations