INDEX

Explanations

words related to assessment of quality and effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Wicidata

-0.76

 MonoBehaviour

-0.71

ⓧ

-0.68

adaptiveStyles

-0.66

 समीक्षाओं

-0.63

 myſelf

-0.61

RefNanny

-0.61

}{@

-0.61

 perfons

-0.60

Spoljašnje

-0.60

POSITIVE LOGITS

ConstraintMaker

0.59

moud

0.54

Delimited

0.54

romolecules

0.51

mintaan

0.51

quoi

0.49

rolid

0.49

idemia

0.48

istique

0.48

vignon

0.47

Activations Density 0.801%

words related to assessment of quality and effectiveness

No Comments

No Known Activations