INDEX

Explanations

instances of phrases indicating an outcome or conclusion

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

transQ

-0.54

 arşivlendi

-0.52

 xenia

-0.51

abestanden

-0.50

XmlEnum

-0.48

tanleria

-0.48

сылкі

-0.47

 تكبرها

-0.47

 дописавши

-0.47



-0.47

POSITIVE LOGITS

<bos>

0.65

 cadeia

0.46

 perfección

0.44

 corresponding

0.42

 península

0.40

 boîte

0.40

NOPQRST

0.38

 auguri

0.38

 seção

0.38

 המש

0.37

Activations Density 0.534%

instances of phrases indicating an outcome or conclusion

No Comments

No Known Activations