INDEX

Explanations

terms related to refugees and immigration experiences

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

Negative Logits

 "..\..\..\

-0.54

 كومونز

-0.53

DoubleQuotes

-0.52

клопе

-0.49

QMetaType

-0.49

 unlocking

-0.48

mpotent

-0.46

 rezult

-0.46

izr

-0.45

 "..\..\

-0.45

POSITIVE LOGITS

 refugees

1.00

 refugee

1.00

 emig

0.94

 Refugee

0.89

 Flücht

0.86

 Refugees

0.86

 immig

0.83

refuge

0.82

 migrants

0.82

 emigrated

0.79

Activations Density 0.397%

terms related to refugees and immigration experiences

No Known Activations