INDEX

Explanations

entities or individuals associated with corruption or legal issues

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

wealthy and powerful individuals, particularly those involved in scandals, corruption, or controversial business dealings.

oai_token-act-pair · claude-4-5-haiku

Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 artigian

-0.37

 udaler

-0.36

Sgt

-0.36

 Kakashi

-0.36

Sgt

-0.35

 manual

-0.34

inheritDoc

-0.34

toarele

-0.34

 Corporal

-0.33

 adipis

-0.33

POSITIVE LOGITS

 billionaire

1.44

 businessman

1.36

 billionaires

1.27

 businessmen

1.24

 tycoon

1.22

 entrepreneur

1.19

 empresario

1.14

businessman

1.14

 philanthropist

1.13

 entrepreneurs

1.03

Activations Density 0.589%

entities or individuals associated with corruption or legal issues

wealthy and powerful individuals, particularly those involved in scandals, corruption, or controversial business dealings.

No Known Activations

entities or individuals associated with corruption or legal issues

wealthy and powerful individuals, particularly those involved in scandals, corruption, or controversial business dealings.

No Known Activations