INDEX

Explanations

structured data representations, particularly lists and arrays

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

ĵ

-1.99

pires

-1.90

§

-1.63

ļ

-1.62

µ

-1.57

ľĵ

-1.54

¤

-1.53

Ĳ

-1.47

protobuf

-1.46

role

-1.42

POSITIVE LOGITS

ening

2.22

horn

1.92

 Items

1.85

eners

1.84

orio

1.70

ured

1.70

ener

1.67

etable

1.66

 Caption

1.62

 item

1.60

Activations Density 0.084%

structured data representations, particularly lists and arrays

No Comments

No Known Activations