INDEX

Explanations

instances of political names and entities in relation to election-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 pandemic

-0.81

 Pandemic

-0.77

 utafitiHapana

-0.70

AccessorTable

-0.68

 Metaverse

-0.67

pandemic

-0.67

Nazionale

-0.66

 Omicron

-0.65

 vaccinated

-0.65

 metaverse

-0.65

POSITIVE LOGITS

 Trump

0.75

Trump

0.65

 Donald

0.60

SaveSave

0.59

 Snapchat

0.57

fileprivate

0.56

 ۲۰۱

0.55

 Zika

0.54

 aDecoder

0.53

 trump

0.53

Activations Density 0.501%

instances of political names and entities in relation to election-related topics

No Comments

No Known Activations