INDEX

Explanations

code structure and definitions for classes and functions in programming contexts

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

Kotlin code: class names, and list/map operations

np_acts-logits-general · gemini-2.0-flash

`. followed by map, filter, or null

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

expandindo

-0.70

帖最后由

-0.70

 correctes

-0.69

ViewImports

-0.66

 Вікі

-0.59

",&

-0.59

 resourceCulture

-0.57

CppMethod

-0.57

VYMaps

-0.55

-------------</

-0.55

POSITIVE LOGITS

(::

0.68

!!

0.60

?:

0.59

("${

0.59

shr

0.58

!!.

0.57

 mutable

0.56

("$

0.54

<*

0.54

kotlin

0.53

Activations Density 0.100%

code structure and definitions for classes and functions in programming contexts

Kotlin code: class names, and list/map operations

`. followed by map, filter, or null

No Comments

No Known Activations