INDEX

Explanations

terms related to hierarchical structures and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

>--}}

-0.70

>");

-0.64

出版年

-0.64

GoogleMap

-0.64

Ārējās

-0.62

;">

-0.57

 Trondheim

-0.57

getMenuInflater

-0.57

 Reine

-0.57

 Golem

-0.56

POSITIVE LOGITS

 desc

2.69

desc

2.63

Desc

2.61

 Desc

2.58

 DESC

2.33

DESC

2.16

descend

1.55

 descend

1.55

 descendant

1.52

Descending

1.49

Activations Density 0.084%

terms related to hierarchical structures and relationships

No Comments

No Known Activations