INDEX

Explanations

first-person expressions and personal opinions

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

Follows "I" or "have"

np_acts-logits-general · gemini-2.0-flash

I have a

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/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.24.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

PyExc

-0.46

 RoutedEventArgs

-0.46

 capacity

-0.43

Huhu

-0.42

WebControls

-0.42

PageContext

-0.42

transQ

-0.42

ResponseWriter

-0.41

 defaultstate

-0.40

 NUKAT

-0.39

POSITIVE LOGITS

 heard

0.47

 emailed

0.46

hear

0.45

assume

0.44

 upvoted

0.44

 grabbed

0.44

heard

0.43

 also

0.43

 mistakenly

0.42

เด

0.41

Activations Density 0.276%

first-person expressions and personal opinions

Follows "I" or "have"

I have a

No Comments

No Known Activations