INDEX

Explanations

structures and relationships within hierarchical data models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

WAUKEE

-0.57

 Standards

-0.57

uco

-0.57

oporosis

-0.56

epoca

-0.56

 אד

-0.55

maphore

-0.55

 hoá

-0.53

érience

-0.53

Standards

-0.52

POSITIVE LOGITS

 getChild

0.96

children

0.85

getChild

0.85

 propOrder

0.84

 children

0.83

CHILD

0.81

ChildIndex

0.81

addChild

0.78

Child

0.78

 childcare

0.77

Activations Density 0.280%

structures and relationships within hierarchical data models

No Comments

No Known Activations