INDEX

Explanations

phrases related to discovering methods or solutions

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

 déterminé

-0.51

 engagé

-0.51

 serez

-0.51

 richiesto

-0.51

HttpMethod

-0.50

ylvania

-0.50

 mercad

-0.49

delu

-0.49

dientemente

-0.49

مصادر

-0.48

POSITIVE LOGITS

 ways

0.67

 ImageIcon

0.63

 agrí

0.56

 ويكيپيديا

0.55

VIATIONS

0.54

 solution

0.54

adze

0.52

ContentAsync

0.52

 Humanos

0.52

parsedMessage

0.52

Activations Density 0.294%

phrases related to discovering methods or solutions

No Comments

No Known Activations