INDEX

Explanations

references to specific film studios and production companies

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

 Normdatei

-0.47

 FixedUpdate

-0.46

 endwhile

-0.45

IRQn

-0.44

 nhật

-0.43

 bread

-0.43

spit

-0.43

 spit

-0.43

 Pager

-0.43

 TabLayout

-0.43

POSITIVE LOGITS

 studios

0.71

 studio

0.64

 Studios

0.60

 Studio

0.56

 STUDIO

0.54

Studio

0.52

bisoft

0.52

 estúdio

0.51

studios

0.51

スタジオ

0.50

Activations Density 0.273%

references to specific film studios and production companies

No Comments

No Known Activations