INDEX

Explanations

programming constructs related to functions and their parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

esez

-0.62

 Administrativna

-0.58

 فريبيس

-0.57

 presidents

-0.53

Tembelea

-0.53

]<<"

-0.51

]<<

-0.51

 thống

-0.51

]='\

-0.51

SpringBootTest

-0.50

POSITIVE LOGITS

 index

1.75

index

1.54

 Index

1.51

Index

1.49

 INDEX

1.33

索引

1.29

 indexes

1.29

INDEX

1.29

 indices

1.26

 indeks

1.24

Activations Density 0.943%

programming constructs related to functions and their parameters

No Comments

No Known Activations