INDEX

Explanations

terms related to significant measurements and variations in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

 somehow

-0.56

__":

-0.53

slightly

-0.50

Slightly

-0.50

@"/

-0.48

ècie

-0.48

出版年

-0.46

 slightly

-0.43

なかなか

-0.43

 Slightly

-0.42

POSITIVE LOGITS

 amount

1.19

amount

0.92

 amounts

0.91

 degree

0.77

 number

0.75

 Amount

0.72

 emphasis

0.72

 cantidad

0.71

amounts

0.70

Amount

0.69

Activations Density 0.914%

terms related to significant measurements and variations in data

No Comments

No Known Activations

terms related to significant measurements and variations in data

No Comments

No Known Activations