INDEX

Explanations

job-related terms and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

<![

-0.48

 XHTML

-0.47

<!--

-0.47

addContainerGap

-0.44

-0.43

<?

-0.43

存于互联网档案馆

-0.42

"));

-0.41

最快更新

-0.41

‪

-0.40

POSITIVE LOGITS

 flex

0.80

flex

0.74

Flex

0.69

 Flex

0.65

 FLEX

0.61

 flexing

0.55

FLEX

0.55

react

0.53

 Styled

0.52

--

0.52

Activations Density 0.106%

job-related terms and data structures

No Comments

No Known Activations