INDEX

Explanations

structured comments or annotations typically found in programming code

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

NOPQRST

-0.50

 mẽ

-0.49

 Pflanze

-0.48

 braccio

-0.47

 تانيه

-0.46

yors

-0.46

CWE

-0.46

MNA

-0.45

сме

-0.45

fromCharCode

-0.45

POSITIVE LOGITS

abestanden

0.78

CloseOperation

0.71

帖最后由

0.69

 kasarigan

0.68

OGND

0.68

évaluateur

0.66

__(/*!

0.66

Geplaatst

0.64

Diwedd

0.62

 Vital

0.62

Activations Density 0.041%

structured comments or annotations typically found in programming code

No Comments

No Known Activations