INDEX

Explanations

references to family and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.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

 estekak

-0.96

 autorytatywna

-0.84

 GenerationType

-0.75

 >=",

-0.75

DoubleQuotes

-0.72

 protoimpl

-0.70

TagMode

-0.70

躇

-0.69

ContentAsync

-0.68

=$?

-0.67

POSITIVE LOGITS

 neighbors

1.45

 neighbours

1.33

 acquaintances

1.31

 neighbor

1.27

 relatives

1.11

 neighbour

1.11

 colleagues

1.03

neighbors

1.03

 Neighbors

1.02

 strangers

1.01

Activations Density 0.350%

references to family and relationships

No Comments

No Known Activations