INDEX

Explanations

the term "core" in various contexts related to health and technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 greateſt

-0.76

atória

-0.75

Efq

-0.74

httphttps

-0.73

 FileReader

-0.72

AccessFile

-0.70

 auffi

-0.69

 Италијани

-0.69

 Picchu

-0.69

 Malabar

-0.67

POSITIVE LOGITS

 core

1.19

 Core

1.17

 cores

1.11

 CORE

1.10

Core

1.04

core

0.99

CORE

0.98

 Cores

0.93

Cores

0.93

cores

0.77

Activations Density 0.056%

the term "core" in various contexts related to health and technology

No Comments

No Known Activations