INDEX

Explanations

headings or section indicators within a structured document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Portail

-0.56

<h1>

-0.54

<bos>

-0.54

 conse

-0.49

</tbody>

-0.49

 body

-0.49

 Steen

-0.46

"]

-0.45

exitRule

-0.44

}{\

-0.44

POSITIVE LOGITS

 intptr

0.84

tagHelperRunner

0.81

mybatisplus

0.77

+#+

0.74

rizona

0.73

 AssemblyCulture

0.72

adə

0.71

 Wiktionnaire

0.71

 disambiguazione

0.70

íncia

0.69

Activations Density 0.026%

headings or section indicators within a structured document

No Comments

No Known Activations