INDEX

Explanations

terms related to medical diagnostics and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

outState

-0.49

 später

-0.44

それと

-0.42

けどね

-0.40

±

-0.40

 później

-0.40

 quien

-0.39

 Just

-0.39

dası

-0.39

それから

-0.39

POSITIVE LOGITS

DeleteBehavior

0.70

 resourceCulture

0.69

Portale

0.68

 AssemblyVersion

0.68

Hentet

0.66

 AttributeSet

0.65

Билгалдахарш

0.64

 IBOutlet

0.61

 otomatig

0.61

 الحره

0.60

Activations Density 0.296%

terms related to medical diagnostics and classifications

No Comments

No Known Activations