INDEX

Explanations

terms related to medical procedures and patient outcomes

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

="_

-1.49

watson

-1.47

-1.45

 herself

-1.37

 Hidden

-1.36

pole

-1.33

osphere

-1.32

 promoters

-1.32

_*

-1.31

Yuk

-1.30

POSITIVE LOGITS

ĻĤ

4.67

Īĺ

4.03

¯

3.98

Į

3.97

¨

3.90

ľĵ

3.90

²

3.86

ĨĴ

3.85

ĥ½

3.82

·

3.75

Activations Density 0.842%

terms related to medical procedures and patient outcomes

No Comments

No Known Activations