INDEX

Explanations

associations with Karachi and political figures or events in Pakistan

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

batore

-0.53

Bangalore

-0.52

Chennai

-0.52

 Bangalore

-0.51

 Chennai

-0.51

 Coimbatore

-0.49

 Tamil

-0.47

BJP

-0.46

ย์

-0.45

APORE

-0.43

POSITIVE LOGITS

 Islamabad

0.98

Personendaten

0.93

 Pakistan

0.88

rungsseite

0.86

lamabad

0.84

 Pakistani

0.81

 provinciale

0.80

 Peshawar

0.79

Pakistan

0.78

 Lahore

0.77

Activations Density 0.066%

associations with Karachi and political figures or events in Pakistan

No Comments

No Known Activations