INDEX

Explanations

names of medical professionals and institutions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 grecque

-0.54

irnov

-0.51

Pyx

-0.46

writeValue

-0.46

 médicale

-0.46

 caviar

-0.46

 اشک

-0.45

heça

-0.45

 Tobago

-0.45

 Soler

-0.44

POSITIVE LOGITS

 Karnataka

0.87

 Bengaluru

0.84

UnusedPrivate

0.81

 Kannada

0.74

ArgsConstructor

0.74

 Bangalore

0.71

новниш

0.69

 Mysore

0.69

calaure

0.67

]")]

0.64

Activations Density 0.089%

names of medical professionals and institutions

No Comments

No Known Activations