INDEX

Explanations

terms related to database schema creation and reverse engineering

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

database schema evolution

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

astify

-0.63

 wireType

-0.60

UserScript

-0.59

 resourceCulture

-0.57

 noDo

-0.55

Personendaten

-0.53

ItemBackground

-0.53

WEBPACK

-0.52

 QtWidgets

-0.52

SpringBootTest

-0.51

POSITIVE LOGITS

Plan

0.40

 plan

0.39

GEBURTSDATUM

0.38

jooq

0.37

plan

0.37

 PLAN

0.36

InputBorder

0.35

 Plan

0.34

Predecesor

0.34

 Blumen

0.32

Activations Density 0.025%

terms related to database schema creation and reverse engineering

database schema evolution

No Comments

No Known Activations