INDEX

Explanations

mathematical terms and phrases that indicate calculations or measurements

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

Text after periods

np_acts-logits-general · gemini-2.0-flash

technical computing and math notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

expandindo

-0.59

@"/

-0.58

⏟

-0.57

Tembelea

-0.53

Parcelize

-0.53

 EconPapers

-0.52

щихся

-0.52

 EClass

-0.52

 beginnetje

-0.51

OGND

-0.50

POSITIVE LOGITS

................

0.53

dersfield

0.52

amica

0.51

 CreateTagHelper

0.51

.-.

0.50

 Peta

0.49

-.-

0.49

 Newswire

0.49

numerusform

0.49

ResponseEntity

0.49

Activations Density 0.098%

mathematical terms and phrases that indicate calculations or measurements

Text after periods

technical computing and math notation

No Comments

No Known Activations