INDEX

Explanations

references to figures, tables, and equations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

 votación

-0.42

tawesome

-0.41

出版年

-0.40

 fieldNum

-0.40

StructEnd

-0.40

ppuden

-0.39

 réguli

-0.39

 staying

-0.39

 jagung

-0.38

ymce

-0.38

POSITIVE LOGITS

??

0.61

~\

0.55

III

0.53

 LABEL

0.51

VI

0.51

IV

0.51

⿴

0.50

VII

0.49

 XIII

0.48

0.47

Activations Density 1.407%

references to figures, tables, and equations within the text

No Comments

No Known Activations