INDEX

Explanations

references to film nominations and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

دانشنامهٔ

-0.52

 AttributeSet

-0.52

 Vikipedi

-0.47

Eft

-0.47

ollectionView

-0.46

 ***!

-0.46

adaptiveStyles

-0.44

crombie

-0.43

celot

-0.43

AndroidJUnit

-0.43

POSITIVE LOGITS

 nomine

0.46

 nominating

0.37

 Nomin

0.37

 nomin

0.36

 nominated

0.36

 avoient

0.36

nominated

0.35

 nominations

0.35

 récomp

0.35

 ganadores

0.35

Activations Density 0.091%

references to film nominations and awards

No Comments

No Known Activations