INDEX

Explanations

references to data structures or collections, specifically maps

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

 Chriftian

-0.80

 nouve

-0.78

ancho

-0.77

RTDA

-0.76

 Monfieur

-0.75

ільки

-0.72

 Paglinawan

-0.71

 offerts

-0.71

ismer

-0.70

 lunghi

-0.70

POSITIVE LOGITS

Map

2.06

Map

2.01

map

1.57

getMap

1.41

 maps

1.32

MAP

1.31

map

1.30

 Maps

1.25

MAP

1.21

ToMap

1.10

Activations Density 0.026%

references to data structures or collections, specifically maps

No Comments

No Known Activations