INDEX

Explanations

code structure and syntax, particularly related to function definitions and parameters

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

Code or data accessing elements by index

np_acts-logits-general · gemini-2.0-flash

indices and indexes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

TestTools

-0.62

Alike

-0.44

ArrowToggle

-0.44

قای

-0.43

قایناق‌لار

-0.42

bootstrapcdn

-0.42

Jeb

-0.42

gwt

-0.42

 kwal

-0.41

 Dernière

-0.41

POSITIVE LOGITS

 index

3.36

 Index

3.06

index

2.99

Index

2.84

 INDEX

2.76

 indexes

2.68

INDEX

2.59

 indices

2.58

 indexing

2.49

 Indexes

2.42

Activations Density 0.152%

code structure and syntax, particularly related to function definitions and parameters

Code or data accessing elements by index

indices and indexes

No Comments

No Known Activations