INDEX

Explanations

references to core functionalities or components in a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Picchu

-0.82

 Мексичка

-0.79

 Dutton

-0.74

زب

-0.73

 RegExp

-0.72

 становника

-0.72

 Bloomfield

-0.71

etera

-0.71

iestety

-0.71

 SDLK

-0.70

POSITIVE LOGITS

 CORE

1.65

 Core

1.56

 core

1.55

core

1.49

 cores

1.48

 Cores

1.42

Cores

1.37

Core

1.37

CORE

1.36

 CoreData

1.17

Activations Density 0.057%

references to core functionalities or components in a system

No Comments

No Known Activations