INDEX

Explanations

terms and expressions related to quantities and measurements

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

Numbers within a sequence or mathematical expression

np_acts-logits-general · gemini-2.0-flash

sequences of numbers

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

Im

-0.46

 immediate

-0.43

Iz

-0.42

bor

-0.41

 wäre

-0.41

ellus

-0.41

 deriving

-0.40

 auto

-0.40

offsetWidth

-0.39

вите

-0.38

POSITIVE LOGITS

GEBURTSDATUM

1.15

 NSCoder

0.99

 beginnetje

0.99

 defaultstate

0.98

ViewFeatures

0.94

ImageContext

0.93

 متعلقه

0.90

OGND

0.88

 ProtoMessage

0.83

FieldBuilder

0.82

Activations Density 0.466%

terms and expressions related to quantities and measurements

Numbers within a sequence or mathematical expression

sequences of numbers

No Comments

No Known Activations