INDEX

Explanations

terms related to training processes and model fitting in machine learning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 instances

-0.57

 instance

-0.54

к

-0.54

 الاطلاع

-0.51

ContentAlignment

-0.49

 Plank

-0.48

ByteBuf

-0.48

Mes

-0.48

‌ش

-0.47

 للا

-0.47

POSITIVE LOGITS

train

1.19

 purpoſe

0.94

 Diſ

0.77

modelBuilder

0.76

complexContent

0.74

exitRule

0.74

 perſon

0.72

TRAIN

0.72

 Houſe

0.70

 ſmall

0.70

Activations Density 0.111%

terms related to training processes and model fitting in machine learning

No Comments

No Known Activations