INDEX

Explanations

terms related to Java annotations and their usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

annotation

-1.70

 annotation

-1.08

 annotations

-1.05

annotations

-0.99

EndContext

-0.94

Annotation

-0.91

 Annotation

-0.90

annotate

-0.83

tagHelperRunner

-0.79

 annot

-0.76

POSITIVE LOGITS

 linkovi

0.52

isible

0.48

gdx

0.47

 volon

0.47

reportWebVitals

0.47

mobileqq

0.46

ymmetric

0.46

лександр

0.45

protector

0.45

cosm

0.45

Activations Density 0.099%

terms related to Java annotations and their usage

No Comments

No Known Activations