INDEX

Explanations

references to "capacity" 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 astore

-0.38

</tfoot>

-0.36

 wuß

-0.36

WidgetItem

-0.36

 TAMBIÉN

-0.35

 slap

-0.33

 nghe

-0.33

lemek

-0.33

Ố

-0.32

esehen

-0.31

POSITIVE LOGITS

 capacity

4.25

 Capacity

3.91

capacity

3.81

Capacity

3.70

 CAPACITY

3.55

 capacities

3.23

CAPACITY

3.05

 capacidad

2.70

 kapasitas

2.61

 capacidade

2.56

Activations Density 0.119%

references to "capacity" in various contexts

No Comments

No Known Activations