INDEX

Explanations

phrases that detail the characteristics or qualities of a product

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 lenker

-0.69

ⓧ

-0.61

NECT

-0.60

']>

-0.60

汰

-0.59

berdayakan

-0.58

 otomatig

-0.58

UGAL

-0.57

isable

-0.57

帖最后由

-0.56

POSITIVE LOGITS

//

0.66

<bos>

0.52

ograma

0.50

awtextra

0.48

TProtocol

0.48

0.47

AddHtmlAttribute

0.46

 layui

0.46

 sputum

0.45

tinyos

0.45

Activations Density 0.146%

phrases that detail the characteristics or qualities of a product

No Comments

No Known Activations