INDEX

Explanations

various forms of scoring or ratings in a context that suggests evaluation or assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

Bre

-0.42

 Jakob

-0.39

Le

-0.39

protoimpl

-0.38

 métier

-0.37

Offic

-0.37

 Wicidata

-0.36

Jakob

-0.36

ahme

-0.35

Especificações

-0.35

POSITIVE LOGITS

getScore

0.59

card

0.59

boards

0.59

lusconi

0.57

oredCriteria

0.56

 score

0.55

 Score

0.54

KommentareTeilen

0.53

BOARD

0.52

cards

0.51

Activations Density 0.080%

various forms of scoring or ratings in a context that suggests evaluation or assessment

No Comments

No Known Activations