INDEX

Explanations

terms and phrases associated with medical procedures and measurements

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

dates and units of measurement

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 stanovnika

-0.46

 שוליים

-0.38

 Marked

-0.34

 pavillon

-0.34

عرِّف

-0.34

bolista

-0.34

Šaltiniai

-0.33

Externé

-0.33

困惑

-0.33

 nota

-0.33

POSITIVE LOGITS

 ब्रेकडाउन

0.73

 &___

0.55

__*/

0.53

OrNil

0.50

+#+

0.50

StructEnd

0.50

contentLoaded

0.49

 neceſſ

0.48

parsedMessage

0.48

󠁴

0.47

Activations Density 0.143%

terms and phrases associated with medical procedures and measurements

dates and units of measurement

No Comments

No Known Activations