INDEX

Explanations

terms related to medical and healthcare fields

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

before fields like "logy," "fore," or "treatment."

np_acts-logits-general · gemini-2.0-flash

noun compounds and collinear phrases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

SequentialGroup

-0.80

ynx

-0.59

Vanjske

-0.55

 muñecas

-0.54

 נוספת

-0.53

 Unito

-0.53

adget

-0.53

 WRIT

-0.53

 surgeon

-0.53

persky

-0.53

POSITIVE LOGITS

 ſtate

0.67

 Roskov

0.65

writeFieldEnd

0.58

Демографія

0.53

Autoritní

0.52

 ftate

0.51

fillType

0.50

 Autorisations

0.49

 tartalomajánló

0.49

клопе

0.48

Activations Density 0.497%

terms related to medical and healthcare fields

before fields like "logy," "fore," or "treatment."

noun compounds and collinear phrases

No Comments

No Known Activations