INDEX

Explanations

programming constructs related to complexity analysis in algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Hochspringen

-0.52

homonymie

-0.52

fxml

-0.51

ագրություններ

-0.50

RefNanny

-0.49

MemoryWarning

-0.48

Exact

-0.47

Entry

-0.47

Przypisy

-0.47

 ujednoznacz

-0.45

POSITIVE LOGITS

mybatisplus

0.59

 protoimpl

0.57

 sprend

0.56

principalTable

0.56

 Referential

0.55

 متحده

0.53

rodu

0.52

SharedModule

0.52

 كومونز

0.51

ppan

0.50

Activations Density 0.075%

programming constructs related to complexity analysis in algorithms

No Comments

No Known Activations