INDEX

Explanations

code snippets and references related to client-server interactions and database management

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

Code-related terms and names

np_acts-logits-general · gemini-2.0-flash

technical class names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

webElementXpaths

-0.55

RegistryLite

-0.54

PyExc

-0.53

 propOrder

-0.48

 Verenig

-0.48

 EClass

-0.47

thoven

-0.47

sizeCache

-0.46

 uska

-0.46

transQ

-0.46

POSITIVE LOGITS

 tarafından

0.76

ⓧ

0.74

 InputDecoration

0.70

 صوتيه

0.66

Przypisy

0.63

principalTable

0.63

 فريبيس

0.62

 DriverManager

0.59

apnews

0.58

 ролях

0.57

Activations Density 0.166%

code snippets and references related to client-server interactions and database management

Code-related terms and names

technical class names

No Comments

No Known Activations