INDEX

Explanations

references to museums or museum-related entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/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.2.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

 slightly

-0.45

 slight

-0.45

AsUp

-0.42

 tenacious

-0.41

CompleteListener

-0.40

enumii

-0.40

Ame

-0.38

anum

-0.38

cách

-0.38

‹

-0.38

POSITIVE LOGITS

 list

0.78

list

0.77

ſelves

0.56

cellation

0.55

 itſelf

0.52

 pleaſure

0.52

ChildScrollView

0.51

 Museum

0.51

ſelf

0.51

List

0.50

Activations Density 0.137%

references to museums or museum-related entities

No Comments

No Known Activations