INDEX

Explanations

references to music artists and albums

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/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.33.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

 Forsch

-0.53

 Speedy

-0.52

+#+#

-0.51

 Infórmanos

-0.49

 anel

-0.48

 sarili

-0.47

 eccell

-0.46

oopy

-0.45

 challenging

-0.45

󠁴

-0.45

POSITIVE LOGITS

DMT

0.42

 Records

0.40

 Recordings

0.40

setArguments

0.39

]")]

0.38

²,

0.38

 setDescription

0.38

ylem

0.38

 setUsername

0.37

 InputDecoration

0.35

Activations Density 0.247%

references to music artists and albums

No Comments

No Known Activations