INDEX

Explanations

specific terminology and calculations related to data training and testing, particularly in machine learning contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CAUSE

-0.47

 arre

-0.46

Cause

-0.45

 ͜ʖ

-0.45

 ссылке

-0.45

Pris

-0.44

 lunak

-0.44

 bedre

-0.44

곤

-0.44

prise

-0.43

POSITIVE LOGITS

TagMode

0.80

RenderAtEndOf

0.79

 train

0.75

 DataLoader

0.71

train

0.71

 Validation

0.70

 validation

0.70

 batches

0.69

 training

0.68

 TRAIN

0.67

Activations Density 0.185%

specific terminology and calculations related to data training and testing, particularly in machine learning contexts

No Comments

No Known Activations