INDEX

Explanations

references to the term "None" or its variations in context

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

providedIn

-0.51

Alfa

-0.48

dominal

-0.48

 pater

-0.47

⤹

-0.46

Fiscal

-0.46

oulder

-0.46

ESL

-0.46

Easter

-0.46

 Fiscal

-0.46

POSITIVE LOGITS

 none

2.38

 None

2.31

None

2.30

none

2.25

 NONE

1.93

NONE

1.78

 ninguno

1.58

 nessuno

1.08

 ninguna

1.07

 neither

1.05

Activations Density 0.126%

references to the term "None" or its variations in context

No Comments

No Known Activations