INDEX

Explanations

indications of warnings or threats towards community members

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

исленность

-0.59

ContentAsync

-0.57

:✨

-0.49

脚注の使い方

-0.48

Демографія

-0.47

تفصیلات

-0.47

المناصب

-0.47

VYMaps

-0.47

contentLoaded

-0.46

 pinulongan

-0.46

POSITIVE LOGITS

遭到

0.88

遭

0.87

 bị

0.86

 facing

0.86

 suffer

0.85

 faced

0.84

被

0.83

 подвер

0.79

 kena

0.77

ถูก

0.77

Activations Density 0.651%

indications of warnings or threats towards community members

No Comments

No Known Activations