INDEX

Explanations

technical terms related to computing, data, and artificial intelligence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ویکی‌پدیای

-0.48

BeginInit

-0.48

Defaults

-0.45

 PropertyChanged

-0.43

iten

-0.42

 anima

-0.42

 flé

-0.41

čnega

-0.41

mockito

-0.40

uk

-0.40

POSITIVE LOGITS

 intptr

0.72

 nakalista

0.71

pagnes

0.68

ⓧ

0.67

 InputDecoration

0.65

קישורים

0.64

postValue

0.62

ContentAsync

0.62

RenderAtEndOf

0.61

Extinguishing

0.60

Activations Density 1.164%

technical terms related to computing, data, and artificial intelligence

No Comments

No Known Activations