INDEX

Explanations

terms related to medical procedures and conditions, particularly in the context of surgery and patient care

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.0.hook_mlp_out

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

»¿

-3.07

ĥ½

-2.98

²

-2.90

Ŀ

-2.90

Ħ

-2.80

³

-2.77

¿½

-2.75

Ĭ

-2.69

ľ

-2.66

Ļª

-2.62

POSITIVE LOGITS

naire

1.82

istor

1.65

ist

1.65

ism

1.58

equation

1.55

 ingredient

1.52

rav

1.49

emption

1.47

 amounts

1.45

face

1.44

Activations Density 0.021%

terms related to medical procedures and conditions, particularly in the context of surgery and patient care

No Comments

No Known Activations