INDEX

Explanations

inquiries related to opinions and reactions about situations or scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 doInBackground

-0.50

 minori

-0.47

ederen

-0.45

se

-0.45

setDo

-0.45

ث

-0.43

 kated

-0.43

Macau

-0.43

 eigenvectors

-0.42

phorus

-0.42

POSITIVE LOGITS

évaluateur

0.73

DockStyle

0.72

 насељу

0.72

IVEREF

0.70

 الحره

0.66

 становника

0.66

verifyException

0.66

 يتيمه

0.65

 CURIAM

0.62

Pues

0.61

Activations Density 0.212%

inquiries related to opinions and reactions about situations or scenarios

No Comments

No Known Activations