INDEX

Explanations

code snippets related to game logic and board manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Comprometido

-0.54

 дописавши

-0.53

GroupLayout

-0.52

SharedDtor

-0.52

errHandler

-0.52

 Baillar

-0.50

 therein

-0.49

WriteLiteral

-0.48

 Mundi

-0.47

cast

-0.47

POSITIVE LOGITS

verwijspagina

0.69

EDEFAULT

0.65

CloseOperation

0.62

 الاطلاع

0.58

rrggbb

0.58

 صوتيه

0.57

rachtet

0.56

 resultCode

0.55

:✨

0.55

SceneManagement

0.54

Activations Density 0.075%

code snippets related to game logic and board manipulation

No Comments

No Known Activations