INDEX

Explanations

references to indigenous or native identity and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ValueStyle

-0.60

BufferException

-0.49

PhysRev

-0.47

 محفوظة

-0.45

irut

-0.43

enumi

-0.43

 مشين

-0.43

verwijspagina

-0.42

enumii

-0.42

tshire

-0.42

POSITIVE LOGITS

 native

2.30

native

2.11

Native

1.99

 Native

1.98

NATIVE

1.70

 natives

1.70

 nativo

1.61

 nativa

1.56

 Natives

1.56

natives

1.46

Activations Density 0.159%

references to indigenous or native identity and related terms

No Comments

No Known Activations