INDEX

Explanations

phrases related to discussions and evaluations in a healthcare or clinical context

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

 ་་

-0.80

ergies

-0.68

 photolibrary

-0.64

 poichè

-0.60

 Diony

-0.59

 Telex

-0.57

PRD

-0.57

 Sched

-0.56

afone

-0.56

 entanto

-0.55

POSITIVE LOGITS

the

1.21

1.08

 some

1.00

 this

0.98

all

0.94

 another

0.94

 many

0.91

 something

0.89

 someone

0.88

 these

0.87

Activations Density 3.084%

phrases related to discussions and evaluations in a healthcare or clinical context

No Comments

No Known Activations