INDEX

Explanations

references to marking or tagging actions and associated elements

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

tenham

-0.82

katapos

-0.75

····

-0.71

satunya

-0.69

'/>

-0.68

氓

-0.66

ドロ

-0.65

 Gauthier

-0.65

 Montagu

-0.65

 indisponible

-0.64

POSITIVE LOGITS

 Marks

1.64

 marks

1.50

Marks

1.46

 MARKS

1.44

 Mark

1.43

 MARK

1.42

 mark

1.41

Mark

1.38

marks

1.33

MARK

1.31

Activations Density 0.091%

references to marking or tagging actions and associated elements

No Comments

No Known Activations