INDEX

Explanations

proper nouns related to people and teams in a sports context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

出版年

-0.50

nodeValue

-0.45

pexpr

-0.42

KommentareTeilen

-0.42

 consulting

-0.41

gapan

-0.41

sizeCache

-0.41

 quanti

-0.41

 talking

-0.40

indexing

-0.40

POSITIVE LOGITS

PerformLayout

0.45

Hentet

0.42

RTEX

0.40

HasAnnotation

0.39

 freshman

0.39

CppMethod

0.39

Fu

0.39

RTSN

0.38

Notae

0.38

 teammate

0.38

Activations Density 0.105%

proper nouns related to people and teams in a sports context

No Comments

No Known Activations