INDEX

Explanations

terms related to audio processing and effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

IsMutable

-0.66

NSIndexPath

-0.64

ſelf

-0.62

出版年

-0.62

 themſelves

-0.62

RegistryLite

-0.61

Personensuche

-0.59

acta

-0.58

 uſed

-0.57

 himſelf

-0.57

POSITIVE LOGITS

GGI

0.50

 background

0.49

fortawesome

0.46

grain

0.46

RPD

0.45

 subtle

0.43

unsch

0.43

าก

0.43

 mergeFrom

0.43

tagHelper

0.42

Activations Density 0.377%

terms related to audio processing and effects

No Comments

No Known Activations