INDEX

Explanations

specific examples and instances within a provided context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

جمعیت

-0.51

 الرياضيه

-0.51

 جغرافيا

-0.49

دانشنامهٔ

-0.45

 Zacks

-0.44

Tembelea

-0.44

 negozio

-0.44

лтемелер

-0.43

 PopupWindow

-0.43

Abitanti

-0.42

POSITIVE LOGITS

principalColumn

0.71

 становника

0.64

 Autorizaciones

0.63

帖最后由

0.59

 createState

0.59

ConstraintMaker

0.57

 Paglinawan

0.56

########.

0.54

WithIdentifier

0.53

\{\\

0.53

Activations Density 1.108%

specific examples and instances within a provided context

No Comments

No Known Activations