INDEX

Explanations

phrases indicating associations or connections between different entities or concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

llo

-1.59

chat

-1.55

uvre

-1.44

genstein

-1.41

 Environment

-1.37

blast

-1.35

tsd

-1.34

 instructed

-1.32

 enabled

-1.30

HS

-1.29

POSITIVE LOGITS

 groups

1.80

 with

1.79

 fields

1.78

 domains

1.76

ities

1.75

 subgroups

1.70

 categories

1.64

 pathways

1.64

 gaps

1.64

 regions

1.63

Activations Density 0.075%

phrases indicating associations or connections between different entities or concepts

No Comments

No Known Activations