INDEX

Explanations

comment syntax across various programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 vPvB

-0.83

 Normdatei

-0.80

 AssemblyCulture

-0.79

 Paglinawan

-0.76

 myſelf

-0.73

 itſelf

-0.73

 linkovi

-0.66

 Meksiku

-0.63

 contextLoads

-0.62



-0.61

POSITIVE LOGITS

0.73

//

0.71

\{\\

0.57

 ско

0.56

بره

0.56

 autorytatywna

0.55

帖最后由

0.54

✨:

0.54

AxisAlignment

0.53

let

0.53

Activations Density 0.057%

comment syntax across various programming languages

No Comments

No Known Activations