INDEX

Explanations

technical terms and descriptions related to performance and quality assessment

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

Lähteet

-0.57

 nini

-0.51

 кӀош

-0.48

 sewa

-0.47

viembre

-0.47

 متعلقه

-0.45

ArgumentParser

-0.45

Maximize

-0.45

 commission

-0.44

gı

-0.44

POSITIVE LOGITS

 >=",

0.70

帖最后由

0.59

DataURL

0.59

ReusableCell

0.57

UseVisualStyle

0.56

.*")]

0.54

 BIBSYS

0.54

 Exactos

0.54

 Horses

0.53

 pacchetto

0.53

Activations Density 0.226%

technical terms and descriptions related to performance and quality assessment

No Comments

No Known Activations