INDEX

Explanations

programming-related syntax and identifiers related to functions and parameters

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

C-style command line argument parsing

np_acts-logits-general · gemini-2.0-flash

command line arguments and request params

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.81

WriteBarrier

-0.66

ніципалі

-0.63

المشاركات

-0.57

adaptiveStyles

-0.55

 JpaRepository

-0.54

 LiveData

-0.54

complexContent

-0.53

ReferenceEquals

-0.53

Sprintf

-0.52

POSITIVE LOGITS

 getopt

0.90

 argv

0.80

argv

0.76

argc

0.71

args

0.69

 args

0.66

 ActivatedRoute

0.65

 argc

0.64

Args

0.64

setArguments

0.62

Activations Density 0.466%

programming-related syntax and identifiers related to functions and parameters

C-style command line argument parsing

command line arguments and request params

No Comments

No Known Activations