INDEX

Explanations

expressions of personal preference or favorites

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

conscious

-1.57

ing

-1.52

iousness

-1.47

innings

-1.47

strength

-1.40

ments

-1.39

ity

-1.38

ities

-1.38

icia

-1.34

 strength

-1.32

POSITIVE LOGITS

ģ

3.82

ľĵ

3.67

º

3.64

<|outofrange|>

3.60

č↵

3.60

↵

3.60

↵

3.60

↵

3.60

↵

3.60

↵

3.60

Activations Density 0.247%

expressions of personal preference or favorites

No Comments

No Known Activations