INDEX

Explanations

references to layout positioning and styles in programming

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 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

 okuyayım

-0.62

={<

-0.56

<eos>

-0.52

NameInMap

-0.49

][

-0.47

and

-0.47

 nove

-0.46

 Earth

-0.45

“

-0.45

(_.

-0.45

POSITIVE LOGITS

 BoxDecoration

1.08

 Location

1.06

Location

1.05

awtextra

1.00

findpost

0.96

 Locations

0.96

 تانيه

0.94

CGRectMake

0.93

 CGRectMake

0.89

RenderAtEndOf

0.88

Activations Density 0.013%

references to layout positioning and styles in programming

No Comments

No Known Activations