INDEX

Explanations

expressions of desire or necessity

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

preceding requirements or desires

np_acts-logits-general · gemini-2.0-flash

needs and wants

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

gridy

-0.47

sendRedirect

-0.46

})`

-0.46

хьтан

-0.43

 جذ

-0.43

aarrggbb

-0.43

Hentet

-0.43

撇

-0.42

 Parse

-0.41

 nook

-0.41

POSITIVE LOGITS

 transfieras

0.48

ViewFeatures

0.47

HideFlags

0.46

ftagPool

0.43

IsContent

0.43

 uLocal

0.42

 TType

0.42

NameInMap

0.40

utenant

0.40

LabelTagHelper

0.40

Activations Density 0.203%

expressions of desire or necessity

preceding requirements or desires

needs and wants

No Comments

No Known Activations