INDEX

Explanations

terms related to postoperative conditions or outcomes

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

ĥ½

-2.70

ĥ

-2.54

↵

-2.48

↵

-2.48

↵

-2.48

<|outofrange|>

-2.48

POSITIVE LOGITS

nikov

1.64

caption

1.46

onant

1.46

ourse

1.45

hev

1.44

ensive

1.39

pective

1.39

oster

1.37

"}](#

1.37

heet

1.37

Activations Density 0.019%

terms related to postoperative conditions or outcomes

No Comments

No Known Activations