INDEX

Explanations

phrases that express a strong sense or perception of emotions or attitudes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Halen

-0.57

atguigu

-0.56

Билгалдахарш

-0.54

fő

-0.53

webElement

-0.53

caris

-0.52

 smtplib

-0.51

 conseguenze

-0.50

 alia

-0.50

等

-0.49

POSITIVE LOGITS

 SENSE

0.99

 sense

0.93

 Sense

0.91

sense

0.90

 Notion

0.75

IsContent

0.72

Sense

0.70

 Serr

0.69

subpackage

0.67

})()

0.67

Activations Density 0.107%

phrases that express a strong sense or perception of emotions or attitudes

No Comments

No Known Activations