INDEX

Explanations

references to machine learning concepts and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Rujuakan

-0.50

SharedDtor

-0.48

 stund

-0.48

elta

-0.47

GeoNames

-0.47

offsetof

-0.46

 veuillez

-0.45

gov

-0.44

 publiques

-0.44

NTIS

-0.43

POSITIVE LOGITS

 betweenstory

0.66

 MainAxisSize

0.64

hematics

0.62

findpost

0.61

MLLoader

0.61

 Roskov

0.59

følgelig

0.59

 FileWriter

0.59

 Lokales

0.58

__':

0.58

Activations Density 0.074%

references to machine learning concepts and methodologies

No Comments

No Known Activations