INDEX

Explanations

references to datasets and their characteristics within a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

pyx

-0.31

ngdoc

-0.31

 cinto

-0.29

lių

-0.28

 главных

-0.28

 ब्रेकडाउन

-0.28

 oír

-0.27

-------

-0.26

 главного

-0.26

 tacón

-0.25

POSITIVE LOGITS

 dataset

0.92

 Dataset

0.86

 datasets

0.85

数据集

0.79

 benchmark

0.79

RegressionTest

0.75

AddHtmlAttribute

0.75

Dataset

0.73

dataset

0.71

 Datasets

0.71

Activations Density 0.599%

references to datasets and their characteristics within a technical context

No Comments

No Known Activations