INDEX

Explanations

elements and themes related to secrecy and hidden information

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelper

-0.55

AnchorTagHelper

-0.52

}],

-0.51

stateProvider

-0.47

っか

-0.43

">'.$

-0.41

setVerticalGroup

-0.41

uc

-0.40

 useRouter

-0.39

여

-0.39

POSITIVE LOGITS

 hidden

1.21

 secret

1.11

 Hidden

1.10

 hiding

1.06

Hidden

1.03

hidden

1.01

 hide

1.00

 Hiding

1.00

 concealment

1.00

 concealed

0.99

Activations Density 0.603%

elements and themes related to secrecy and hidden information

No Comments

No Known Activations