INDEX

Explanations

terms related to "core" components and their attributes in a technical context

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

 Мексичка

-0.76

 Picchu

-0.74

 HasFactory

-0.74

scrapy

-0.73

 Loomis

-0.73

 Bloomfield

-0.72

زب

-0.71



-0.71

HasBeenSet

-0.71

 uſed

-0.71

POSITIVE LOGITS

 CORE

1.69

 Core

1.61

 core

1.60

core

1.54

 cores

1.51

 Cores

1.45

CORE

1.42

Core

1.40

Cores

1.39

 CoreData

1.21

Activations Density 0.034%

terms related to "core" components and their attributes in a technical context

No Comments

No Known Activations