INDEX

Explanations

references to educational materials and textbooks, particularly in the context of teaching and learning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

发表于

-0.62

homonymie

-0.62

principalColumn

-0.61

曖昧さ回避

-0.57

 handleMessage

-0.54

KommentareTeilen

-0.54

cheduler

-0.54

afficheront

-0.54

 nitrates

-0.52

complexContent

-0.52

POSITIVE LOGITS

 textbook

0.97

 textbooks

0.81

 Textbook

0.78

Textbook

0.75

text

0.71

 text

0.70

 Prentice

0.65

 chapter

0.64

 chapters

0.63

 texts

0.60

Activations Density 0.262%

references to educational materials and textbooks, particularly in the context of teaching and learning

No Comments

No Known Activations