INDEX

Explanations

programming-related terms, particularly those involving functions and properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ográficos

-0.61

 mouseY

-0.55

 thought

-0.53

ercises

-0.52

ruct

-0.52

urma

-0.51

 Chuk

-0.50

$=$

-0.49

 Thought

-0.49

urs

-0.48

POSITIVE LOGITS

ContentAsync

0.75

 للمعارف

0.65

 AssemblyCulture

0.64

脚注の使い方

0.63

().

0.62

 فريبيس

0.61

ftagPool

0.59

archiviato

0.59

()}

0.59

 useDispatch

0.58

Activations Density 0.112%

programming-related terms, particularly those involving functions and properties

No Comments

No Known Activations