INDEX

Explanations

references to figures and tables in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ęż

-0.49

 rate

-0.47

ú

-0.44

-0.43

...

-0.42

pro

-0.41

"${

-0.41

?>/

-0.41

]=="

-0.40

or

-0.40

POSITIVE LOGITS

Datuak

1.21

setVerticalGroup

1.12

 صوتيه

1.08

 initComponents

1.05

HostException

0.92

 surla

0.91

MemoryWarning

0.91

Tikang

0.91

djangoproject

0.89

InjectAttribute

0.89

Activations Density 0.132%

references to figures and tables in the document

No Comments

No Known Activations