INDEX

Explanations

database-related terms and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 setAddress

-0.45

WriteLiteral

-0.45

 Rosal

-0.44

IVEREF

-0.41

Біографія

-0.39

Guten

-0.39

industan

-0.38

 Gode

-0.38

 alimentaires

-0.38

CppMethod

-0.37

POSITIVE LOGITS

 players

1.55

 Players

1.48

 teams

1.48

 game

1.44

 games

1.43

Players

1.42

 Team

1.42

 team

1.42

 Teams

1.40

Team

1.40

Activations Density 0.155%

database-related terms and operations

No Comments

No Known Activations