INDEX

Explanations

conjunctions that indicate a relationship between multiple items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تقاوى

-0.54

RegressionTest

-0.53

المناصب

-0.52

ContentAsync

-0.51

 للمعارف

-0.50

으며

-0.49

ValueStyle

-0.48

NameInMap

-0.48

Autoritní

-0.47

 незавершена

-0.46

POSITIVE LOGITS

 disponibilités

0.42

JP

0.38

Weil

0.38

叫

0.37

ڤ

0.37

fml

0.36

dra

0.36

 Vries

0.36

obj

0.35

Dra

0.35

Activations Density 0.437%

conjunctions that indicate a relationship between multiple items or concepts

No Comments

No Known Activations