INDEX

Explanations

references to specific biological structures or compartments, particularly in the context of membranes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 TestBed

-0.83

ReusableCell

-0.82

 nonatomic

-0.80

 الحره

-0.74

NameInMap

-0.70

 HasFactory

-0.70

 ename

-0.69

DispatchToProps

-0.69

 Ename

-0.69

 IndexPath

-0.67

POSITIVE LOGITS

 sector

0.72

 Council

0.71

 sectors

0.66

sector

0.66

Sector

0.65

 Sector

0.62

Council

0.59

UNCIL

0.55

 sectores

0.53

 Sectors

0.53

Activations Density 0.133%

references to specific biological structures or compartments, particularly in the context of membranes

No Comments

No Known Activations