INDEX

Explanations

references to programming structures and components related to data processing and application functionality

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-0.90

 ProtoMessage

-0.63

MemoryWarning

-0.60

expandindo

-0.58

 resourceCulture

-0.58

complexContent

-0.56

DockStyle

-0.56

 الحره

-0.55

SequentialGroup

-0.53

 surla

-0.53

POSITIVE LOGITS

ux

0.41

and

0.39

 timestamps

0.39

Ret

0.39

 deadlines

0.38

Chham

0.38

 Channel

0.38

Med

0.37

 guar

0.37

abs

0.37

Activations Density 0.144%

references to programming structures and components related to data processing and application functionality

No Comments

No Known Activations