INDEX

Explanations

references to the action of deleting or removing items in code or data structures

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

Code related to deletion

np_acts-logits-general · gemini-2.0-flash

delete

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

Diweddarwch

-0.61

pexpr

-0.59

 gehalten

-0.53

يكب

-0.51

agos

-0.51

atisk

-0.51

تيجة

-0.51

empatan

-0.50

 AspNetCore

-0.49

logrus

-0.49

POSITIVE LOGITS

DeleteMapping

0.98

 deleteAll

0.75

handleDelete

0.74

btnDelete

0.71

 DELETE

0.67

 Diſ

0.67

DeleteBehavior

0.66

Xoa

0.65

Fø

0.65

 Delete

0.64

Activations Density 0.067%

references to the action of deleting or removing items in code or data structures

Code related to deletion

delete

No Comments

No Known Activations