INDEX

Explanations

occurrences of indexing or structure notation in programming contexts

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

"index" and "idx" keywords

np_acts-logits-general · gemini-2.0-flash

index, idx

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UserScript

-0.45

ฒ

-0.44

 gdyby

-0.43

 bVar

-0.42

hept

-0.41

 gouvern

-0.40

toHaveBeenCalled

-0.40

brev

-0.39

 getApplication

-0.39

 gobern

-0.39

POSITIVE LOGITS

 Index

1.39

 index

1.38

Index

1.24

 INDEX

1.23

index

1.21

getIndex

1.09

INDEX

1.09

 indexes

1.01

 Indexing

1.00

 getIndex

1.00

Activations Density 0.217%

occurrences of indexing or structure notation in programming contexts

"index" and "idx" keywords

index, idx

No Comments

No Known Activations