INDEX

Explanations

references to political administrations and their policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Autoritní

-0.42

 feedback

-0.36

 guys

-0.35

pital

-0.34

slidesToShow

-0.33

pit

-0.32

Guys

-0.32

feedback

-0.32

RemoveField

-0.32

 muscles

-0.31

POSITIVE LOGITS

 administration

0.63

administration

0.62

 amminist

0.61

sonaro

0.60

 regering

0.59

 Administration

0.58

 regime

0.57

 Obrador

0.57

 dictadura

0.57

 kasarigan

0.56

Activations Density 0.255%

references to political administrations and their policies

No Comments

No Known Activations