INDEX

Explanations

references to political events and figures

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

 Obrador

-0.49

 Hezbollah

-0.48

 gawas

-0.47

ghted

-0.46

rž

-0.44

✭✭

-0.44

 "..\..\..\

-0.44

chka

-0.43

redge

-0.42

 fica

-0.42

POSITIVE LOGITS

 colonial

0.80

Colonial

0.70

 Colonial

0.70

colonial

0.70

AndEndTag

0.69

colony

0.67

liesslich

0.63

 Protector

0.62

 colonies

0.62

'}>

0.61

Activations Density 0.440%

references to political events and figures

No Comments

No Known Activations