INDEX

Explanations

details related to activities undertaken or actions witnessed in various contexts

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

])));

-0.69

 BorderSide

-0.55

 compétence

-0.54

DockStyle

-0.54

$_['

-0.53

ErrUnexpectedEOF

-0.53

BagConstraints

-0.53

SpringBootTest

-0.51

mybatisplus

-0.51

קישורים

-0.51

POSITIVE LOGITS

__':

0.68

rovna

0.68

 Paglinawan

0.66

 innocently

0.64

ふと

0.60

__':

0.57

 afternoon

0.56

たまたま

0.56

 evening

0.55

elesai

0.51

Activations Density 0.189%

details related to activities undertaken or actions witnessed in various contexts

No Comments

No Known Activations