INDEX

Explanations

function calls related to program termination and exit status

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

"exit" after "return" or "(" in C code

np_acts-logits-general · gemini-2.0-flash

program termination

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 <=",

-0.64

 للمعارف

-0.63

ⓧ

-0.55

 المعيارى

-0.54

 EconPapers

-0.54

WaitGroup

-0.54

BufferException

-0.53

 دیکھیے

-0.52

يميديا

-0.51

Hochspringen

-0.51

POSITIVE LOGITS

 contextLoads

0.66

 Majefty

0.63

 defire

0.59

 ſtate

0.59

 ftate

0.57

 perfons

0.57

 caufe

0.56

 Chriftian

0.56

 ſmall

0.54

Efq

0.54

Activations Density 0.141%

function calls related to program termination and exit status

"exit" after "return" or "(" in C code

program termination

No Comments

No Known Activations