INDEX

Explanations

instances of familial relationships and associated terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ThemeData

-0.51

❹

-0.44

 GenerationType

-0.43

 informée

-0.41

AndEndTag

-0.40

CppCodeGen

-0.40

봤

-0.40

upon

-0.39

quelize

-0.38

Titre

-0.38

POSITIVE LOGITS

Personendaten

0.45

 relationships

0.45

 partner

0.41

taminophen

0.41

 AppCompatTheme

0.40

vgili

0.40

 للمعارف

0.40

VIT

0.39

Rela

0.39

 relationship

0.39

Activations Density 0.502%

instances of familial relationships and associated terms

No Comments

No Known Activations