INDEX

Explanations

phrases that reference specific entities or elements in a context, indicated by the frequent occurrence of the word "which."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

featureID

-0.49

Referencie

-0.46

titleMargin

-0.45

forChild

-0.45

RegressionTest

-0.43

Odkazy

-0.43

GTCX

-0.42

tyfik

-0.41

 Crochet

-0.41

утбо

-0.40

POSITIVE LOGITS

出版年

0.57

 satunya

0.57

antaranya

0.54

 antaranya

0.47

ArgsConstructor

0.46

 diantaranya

0.46

 ustedes

0.43

 daarvan

0.43

 يتيمه

0.42

 solches

0.42

Activations Density 0.307%

phrases that reference specific entities or elements in a context, indicated by the frequent occurrence of the word "which."

No Comments

No Known Activations