INDEX

Explanations

details about military incidents and casualties

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

 Eich

-0.61

 Mika

-0.49

 Brésil

-0.48

σθαι

-0.48

 isle

-0.47

yer

-0.47

 Quint

-0.46

 חיצוניים

-0.44

brows

-0.44

ladolid

-0.44

POSITIVE LOGITS

 Afghanistan

1.52

 Afghan

1.47

 Kabul

1.45

 Taliban

1.38

Afghanistan

1.36

Afghan

1.30

 afghan

1.25

 Afgan

1.19

 Afghans

1.18

ABUL

1.10

Activations Density 0.086%

details about military incidents and casualties

No Comments

No Known Activations