INDEX

Explanations

words indicating any possibility or potential across various contexts

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

"Any" followed by a noun

np_acts-logits-general · gemini-2.0-flash

any or anyone followed by word

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

 समीक्षाएं

-0.68

findpost

-0.65

GraphicsUnit

-0.60

новниш

-0.55

Népesség

-0.53

!*\

-0.52

ueuse

-0.50

 agrí

-0.50

ArgsConstructor

-0.49

 MessageBoxIcon

-0.49

POSITIVE LOGITS

 anyone

1.16

Any

1.11

Any

1.10

any

1.10

 anybody

1.07

anyone

1.05

 whatsoever

1.05

 Anyone

1.05

 qualquer

1.04

Anyone

1.03

Activations Density 0.308%

words indicating any possibility or potential across various contexts

"Any" followed by a noun

any or anyone followed by word

No Comments

No Known Activations