INDEX

Explanations

mathematical expressions related to probability and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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



-0.94

Personendaten

-0.92

 Roskov

-0.81

 ComVisible

-0.81

enderror

-0.78

 estekak

-0.78

LookAnd

-0.77

OGND

-0.73

 cherchés

-0.72

 ویکی‌پدی

-0.72

POSITIVE LOGITS

0.39

to

0.35

 glück

0.30

 terle

0.28

[toxicity=0]

0.28

 laborales

0.27

 nonetheless

0.26

那是

0.25

 estuviera

0.25

Activations Density 0.120%

mathematical expressions related to probability and statistics

No Comments

No Known Activations