INDEX

Explanations

terms related to data processing and analysis in programming contexts

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 forehead

-0.59

-0.57

TryParse

-0.56

 ***!

-0.55

niająca

-0.55

ReusableCell

-0.53

 kasarigan

-0.52

 square

-0.51

addCriterion

-0.51

 Paglinawan

-0.50

POSITIVE LOGITS

 يتيمه

0.55

.*")]

0.52

execSQL

0.51

 Buffer

0.51

 Dracula

0.50

tomans

0.48

Delimited

0.47

 tartalomajánló

0.46

 ditutup

0.46

 مشارکت‌کنندگان

0.44

Activations Density 0.410%

terms related to data processing and analysis in programming contexts

No Comments

No Known Activations