INDEX

Explanations

code snippets and structured data elements

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/2-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.2.hook_mlp_out

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

vell

-1.49

rapeutics

-1.44

 WARRANTIES

-1.39

 properly

-1.38

 yourself

-1.38

 themselves

-1.36

 Dental

-1.34

jections

-1.33

 shortage

-1.33

arming

-1.32

POSITIVE LOGITS

feld

1.67

agra

1.55

 calculus

1.53

ius

1.48

grade

1.43

mate

1.42

naire

1.41

meg

1.41

 clar

1.40

imeters

1.38

Activations Density 0.169%

code snippets and structured data elements

No Comments

No Known Activations