INDEX

Explanations

programming-related terminology, particularly related to layout management and user interface components

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

Punctuation and symbols within code or URLs

np_acts-logits-general · gemini-2.0-flash

code separators/boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

-0.47

#+#

-0.47

 cạnh

-0.47

 distance

-0.46

Климат

-0.44

to

-0.43

hamcrest

-0.42

高考

-0.42

下载附件

-0.42

POSITIVE LOGITS

$.

0.71

NUMX

0.70

 تضيفلها

0.70

AnchorStyles

0.70

writeField

0.69

 nôtre

0.69

 étoient

0.68

 avoient

0.64

uxxxx

0.64

 étoit

0.63

Activations Density 0.081%

programming-related terminology, particularly related to layout management and user interface components

Punctuation and symbols within code or URLs

code separators/boundaries

No Comments

No Known Activations