INDEX

Explanations

expressions related to surprise or interest in events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 contextLoads

-0.57

 tartalomajánló

-0.54

IContainer

-0.49

 незавершена

-0.48

 propOrder

-0.46

 kasarigan

-0.45

最快更新

-0.44

تقاوى

-0.42

Hentet

-0.42

 стаття

-0.41

POSITIVE LOGITS

 inter

0.47

évaluateur

0.46

 extent

0.44

culously

0.43

webElementXpaths

0.41

 Testi

0.40

 Exacts

0.39

Interestingly

0.38

 Interestingly

0.38

 Inter

0.38

Activations Density 0.364%

expressions related to surprise or interest in events or situations

No Comments

No Known Activations

expressions related to surprise or interest in events or situations

No Comments

No Known Activations