INDEX

Explanations

function and option-related programming constructs in code documentation

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

Tokens appearing with code-related words

np_acts-logits-general · gemini-2.0-flash

options parameter

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.73

 resourceCulture

-0.71

LookAnd

-0.69

 HasFactory

-0.64

 GetEnumerator

-0.63

SourceChecksum

-0.63

thâu

-0.63

 Wikimedijinoj

-0.62

WriteBarrier

-0.61

HideFlags

-0.60

POSITIVE LOGITS

 متعلقه

0.59

 InputDecoration

0.56

 Battista

0.53

WriteTagHelper

0.49

 Lodging

0.48

mendation

0.48

antMatchers

0.47

onents

0.47

Vos

0.47

CHANGED

0.46

Activations Density 0.266%

function and option-related programming constructs in code documentation

Tokens appearing with code-related words

options parameter

No Comments

No Known Activations