INDEX

Explanations

terms related to programming concepts and errors

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

 called

-1.51

 held

-1.47

aws

-1.38

 moth

-1.37

chos

-1.37

 needed

-1.34

 includes

-1.34

 Canadians

-1.32

 susp

-1.30

 equipped

-1.30

POSITIVE LOGITS

amente

1.71

 Discussion

1.51

(@

1.50

igent

1.44

(@

1.44

issance

1.40

 lane

1.40

Ĵ

1.38

wikipedia

1.37

 Rehabilitation

1.36

Activations Density 1.229%

terms related to programming concepts and errors

No Comments

No Known Activations