INDEX

Explanations

patterns of punctuation and formatting

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

Followed by numerical digits

np_acts-logits-general · gemini-2.0-flash

legal document citations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ed

-0.92

 تضيفلها

-0.77

Tikang

-0.73

ChildScrollView

-0.71

aarrggbb

-0.71

 Suff

-0.69

 Barna

-0.67

 /\.(

-0.67

InputBorder

-0.66

voorbeeld

-0.65

POSITIVE LOGITS

↵↵↵

1.34

にほんブログ村

1.02

 Rous

0.80

-------

0.79

 Stande

0.79

 ſhall

0.76

 Chriſt

0.73

↵↵↵↵

0.71

 débris

0.70

$-$\\

0.69

Activations Density 0.126%

patterns of punctuation and formatting

Followed by numerical digits

legal document citations

No Comments

No Known Activations