INDEX

Explanations

mathematical notations and symbols associated with functions and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 vertical

-0.47

Vertical

-0.44

原始内容存档于

-0.43

vertical

-0.42

ことです

-0.40

ైన

-0.39

彰

-0.38

 dismissed

-0.38

roj

-0.38

 bota

-0.37

POSITIVE LOGITS

LookAnd

1.07

Personendaten

1.03

 kaarangay

1.00

########.

0.99

 EconPapers

0.99

 cherchés

0.96

sizeCache

0.93

 NSCoder

0.90

ⓧ

0.88

awtextra

0.88

Activations Density 0.414%

mathematical notations and symbols associated with functions and parameters

No Comments

No Known Activations