INDEX

Explanations

terms related to occupation and power dynamics in conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Trenton

-0.54

 Kandy

-0.51

insertBefore

-0.51

+:+

-0.48

 reflected

-0.48

fromCharCode

-0.44

ьа

-0.43

ngdoc

-0.43

 based

-0.41

 Murcia

-0.41

POSITIVE LOGITS

 occupied

0.78

occupied

0.76

omock

0.73

 Occupied

0.71

 infested

0.71

 deserted

0.69

锈钢

0.67

Haunted

0.67

 nahilalakip

0.67

 populated

0.67

Activations Density 0.835%

terms related to occupation and power dynamics in conflicts

No Comments

No Known Activations