INDEX

Explanations

references to system components and error handling in programming contexts

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

Followed by a class, object, or math related token

np_acts-logits-general · gemini-2.0-flash

commons.math

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

SequentialGroup

-0.81

ViewImports

-0.77

AndEndTag

-0.69

fromCharCode

-0.69

 typelib

-0.65

HasForeignKey

-0.65

PageFactory

-0.62

requestCode

-0.62

resave

-0.62

RemoteException

-0.62

POSITIVE LOGITS

ukone

0.85

 "..\..\

0.73

0.64

 "..\..\..\

0.63

Inv

0.63

 للمعارف

0.62

')[

0.61

".

0.59

Activations Density 0.140%

references to system components and error handling in programming contexts

Followed by a class, object, or math related token

commons.math

No Comments

No Known Activations