INDEX

Explanations

references to ancient history or civilizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Normdatei

-0.50



-0.49

 cordon

-0.47

Interv

-0.44

 Sixt

-0.43

,$_

-0.43

 Reſ

-0.42

regime

-0.41

Lid

-0.41

 Administ

-0.41

POSITIVE LOGITS

 ancient

1.70

 Ancient

1.62

Ancient

1.56

ancient

1.55

 ANCI

1.21

 древ

1.15

 ancients

1.06

古代

1.05

 antichi

0.96

ANCI

0.85

Activations Density 0.059%

references to ancient history or civilizations

No Comments

No Known Activations