INDEX

Explanations

references to units and measurements in various contexts

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

 Públicas

-0.51

 Перейти

-0.50

NamedQueries

-0.47

]=='

-0.46

-0.44

⋙

-0.42

]=="

-0.42

三四

-0.40

 navideñas

-0.40

󠁣

-0.40

POSITIVE LOGITS

 unit

2.59

 Unit

2.42

Unit

2.38

unit

2.34

 units

2.27

 Units

2.25

Units

2.13

 UNIT

2.13

units

2.08

UNIT

2.05

Activations Density 0.102%

references to units and measurements in various contexts

No Comments

No Known Activations