INDEX

Explanations

expressions of appreciation and positive emotions in interpersonal interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 препратки

-0.50

 Preußen

-0.48

Бахар

-0.47

(&$

-0.47

ویزی

-0.47

 TestBed

-0.46

 likely

-0.45

 копия

-0.45

complexType

-0.43

皙

-0.43

POSITIVE LOGITS

 rasanya

0.66

ExecuteReader

0.64

 EconPapers

0.63

 feels

0.62

reszcie

0.62

feels

0.61

いざ

0.60

HideFlags

0.59

experience

0.58

UIControlState

0.57

Activations Density 0.208%

expressions of appreciation and positive emotions in interpersonal interactions

No Comments

No Known Activations