INDEX

Explanations

words associated with loyalty and uniqueness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

 vectorielles

-0.52

 againſt

-0.50

RegressionTest

-0.49

 Anſ

-0.47

featureID

-0.46

 ménages

-0.46

曖昧さ回避

-0.44

 Inſ

-0.44

Rüyada

-0.44

**/

-0.43

POSITIVE LOGITS

 GenerationType

0.61

opt

0.57

bn

0.56

 loyal

0.54

 loyalty

0.50

nith

0.49

 Administrativna

0.48

 Loyalty

0.46

 Loyal

0.46

fetchall

0.45

Activations Density 0.163%

words associated with loyalty and uniqueness

No Comments

No Known Activations