INDEX

Explanations

expressive words indicating personal feelings and emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 فريبيس

-0.57

łec

-0.53

 MediatR

-0.52

DataAnnotations

-0.51

]<<"

-0.51

 المعيارى

-0.51

 initComponents

-0.51

 psychosis

-0.51

ValueStyle

-0.49

 Pollack

-0.49

POSITIVE LOGITS

 חיצוניים

0.74

ollectionView

0.68

 wondered

0.65

ⓧ

0.61

 wonder

0.59

 reminded

0.57

 wonders

0.56

bet

0.56

 häm

0.55

 interviewed

0.55

Activations Density 0.302%

expressive words indicating personal feelings and emotions

No Comments

No Known Activations