INDEX

Explanations

Java programming language constructs related to class definitions and methods

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

Java/Android code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ties

-0.47

 utafitiHapana

-0.39

tie

-0.38

 biologique

-0.34

pann

-0.34

дарю

-0.34

 remind

-0.33

ále

-0.33

商品説明

-0.32

sipasi

-0.32

POSITIVE LOGITS

setArguments

0.68

 getArguments

0.62

MLLoader

0.59

onAttach

0.55

 ſta

0.50

WithIOException

0.48

 faſt

0.48

 StatefulWidget

0.47

InitVars

0.47

 newInstance

0.47

Activations Density 0.002%

Java programming language constructs related to class definitions and methods

Java/Android code snippets

No Comments

No Known Activations