INDEX

Explanations

references to medical conditions and their assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nahilalakip

-0.77

 Мексичка

-0.70

=$?

-0.70

tagHelperRunner

-0.69

windowFixed

-0.65

 odkazy

-0.65

 itſelf

-0.64

 disambiguazione

-0.63

 ་་

-0.62

}],

-0.62

POSITIVE LOGITS

 someone

3.16

someone

2.94

 somebody

2.79

Someone

2.71

 Someone

2.61

somebody

2.50

 SOMEONE

2.29

 alguien

2.27

Somebody

2.25

 quelqu

2.25

Activations Density 0.498%

references to medical conditions and their assessment

No Comments

No Known Activations