INDEX

Explanations

various lengths and details about documentaries or films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

-0.43

évaluateur

-0.42

addCriterion

-0.41

 تضيفلها

-0.40

<?

-0.38



-0.37

mbggenerated

-0.37

yntaxException

-0.36

 Haushalt

-0.35

InitStruct

-0.35

POSITIVE LOGITS

 lengthy

0.63

 length

0.59

 full

0.55

 duration

0.52

 novella

0.52

jor

0.51

spiel

0.50

 duración

0.50

LENGTH

0.49

Dauer

0.49

Activations Density 0.381%

various lengths and details about documentaries or films

No Comments

No Known Activations