INDEX

Explanations

references to neighbors and neighboring relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

retan

-0.69

hradun

-0.67

 Merle

-0.65

 Crews

-0.63

 professionnelle

-0.62

unschweig

-0.62

 Fuego

-0.61

-------------</

-0.61

 Gutiérrez

-0.61

SError

-0.61

POSITIVE LOGITS

 neighbors

1.56

 neighbor

1.45

 neigh

1.39

 NEIGH

1.35

 neighbours

1.33

 Neighbor

1.29

 neighborhood

1.26

 Neigh

1.24

 neighbour

1.21

 neighboring

1.21

Activations Density 0.079%

references to neighbors and neighboring relationships

No Comments

No Known Activations