INDEX

Explanations

questions or inquiries related to reasons and motivations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 fubject

-0.52

LLocation

-0.52

bootstrapcdn

-0.50

 Courant

-0.50

annica

-0.50

linson

-0.49

rss

-0.48

 section

-0.48

CBM

-0.47

 poffe

-0.47

POSITIVE LOGITS

why

1.56

why

1.46

Why

1.46

Why

1.42

WHY

1.28

WHY

1.28

 pourquoi

1.15

 Pourquoi

1.13

 Warum

1.11

 Whyte

1.10

Activations Density 0.060%

questions or inquiries related to reasons and motivations

No Comments

No Known Activations