INDEX

Explanations

references to training datasets and their characteristics 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

HomeAsUpEnabled

-0.90

UnusedPrivate

-0.87

MigrationBuilder

-0.80

 мәкал

-0.77

DebuggerStep

-0.76

bitField

-0.74

GIVEREF

-0.71

nonatomic

-0.70

AndEndTag

-0.69

 مشين

-0.69

POSITIVE LOGITS

 dataset

0.61

datasets

0.54

数据集

0.52

 data

0.49

 datasets

0.48

data

0.48

dataset

0.45

 samples

0.44

 plaintiffs

0.44

Välislingid

0.43

Activations Density 0.484%

references to training datasets and their characteristics in machine learning contexts

No Comments

No Known Activations