INDEX

Explanations

terms related to forensic audio analysis and signal processing

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

academic research methods

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 /*#__

-0.42

Serviço

-0.33

nameof

-0.31

 pazi

-0.31

APM

-0.30

参

-0.30

CIP

-0.30

놨

-0.30

 nyug

-0.30

srand

-0.29

POSITIVE LOGITS

 للاسماء

0.67

 Infórmanos

0.55

 topics

0.55

ніципалі

0.53

 Conferencia

0.52

 applications

0.52

 developments

0.50

 AppCompatTheme

0.50

ご理解

0.50

Portail

0.50

Activations Density 0.016%

terms related to forensic audio analysis and signal processing

academic research methods

No Comments

No Known Activations