INDEX

Explanations

elements related to behind-the-scenes production and actor experiences

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

rungsseite

-0.64

 automatiques

-0.52

 électroniques

-0.51

 søndag

-0.48

 civile

-0.48

 étoit

-0.45

 actualidad

-0.44

 bricolaje

-0.44

 corrupción

-0.44

AndEndTag

-0.43

POSITIVE LOGITS

 director

0.56

 casting

0.50

 cast

0.49

GEBURTSDATUM

0.49

 script

0.48

director

0.47

 firing

0.46

 interpret

0.46

 romp

0.46

 scene

0.45

Activations Density 0.262%

elements related to behind-the-scenes production and actor experiences

No Comments

No Known Activations