INDEX

Explanations

references to time and sequence of events in processes or studies

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

 credibility

-1.47

anse

-1.46

stalk

-1.37

OUS

-1.36

derer

-1.35

esses

-1.34

opard

-1.31

bsite

-1.29

ume

-1.29

 Fighter

-1.27

POSITIVE LOGITS

ĻĤ

4.67

↵

4.55

č↵

4.55

↵

4.55

č↵

4.55

<|outofrange|>

4.55

č↵

4.55

Activations Density 0.144%

references to time and sequence of events in processes or studies

No Comments

No Known Activations