INDEX

Explanations

HTML tags or coding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Personendaten

-0.52

pa

-0.48

-0.45

xtick

-0.45

ps

-0.43

 onCreateView

-0.43

 europea

-0.42

 SafeMath

-0.42

ers

-0.42

lager

-0.41

POSITIVE LOGITS

出版年

0.97

 resourceCulture

0.89

extAlignment

0.75

 ddelweddau

0.75

 فريبيس

0.71

 صوتيه

0.69

SwitchCompat

0.68

Hentet

0.68

0.67

AccessorTable

0.67

Activations Density 0.059%

HTML tags or coding elements

No Comments

No Known Activations