INDEX

Explanations

references to personal experiences and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 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

 iprot

-0.59

 kasarigan

-0.55

الحياه

-0.55

Geplaatst

-0.51

NameInMap

-0.49

makeConstraints

-0.47

رشف

-0.46

GenerationType

-0.46

OGND

-0.46

isContained

-0.45

POSITIVE LOGITS

mybatisplus

0.40

ynb

0.39

Bingo

0.36

rrggbb

0.35

 withal

0.35

 satis

0.34

ACGIH

0.34

brak

0.33

 Rate

0.33

 Refund

0.33

Activations Density 1.032%

references to personal experiences and preferences

No Comments

No Known Activations