INDEX

Explanations

code-related terms and structures

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

Code snippets and programming-related text

np_acts-logits-general · gemini-2.0-flash

whether it is instance of types

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

stehen

-0.52

flatMap

-0.50

if

-0.50

 pasado

-0.48

lak

-0.48

ุด

-0.47

if

-0.46

гава

-0.45

 past

-0.45

or

-0.45

POSITIVE LOGITS

IsPostBack

0.75

mybatisplus

0.68

 contextLoads

0.62

UnusedPrivate

0.62

expandindo

0.61

AndEndTag

0.61

yntaxException

0.61

+#+#

0.60

 kasarigan

0.60

DockStyle

0.59

Activations Density 0.045%

code-related terms and structures

Code snippets and programming-related text

whether it is instance of types

No Comments

No Known Activations