INDEX

Explanations

dates and years in texts

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

idious

-1.56

ying

-1.54

 certain

-1.46

rends

-1.46

 arms

-1.41

 probing

-1.40

too

-1.39

ests

-1.39

 nature

-1.37

 familiar

-1.35

POSITIVE LOGITS

¦

3.07

¾

2.78

ĥ½

2.75

¨

2.60

®

2.38

Ń

2.35

¡

2.32

»

2.22

Ľ

2.19

ł

2.19

Activations Density 0.139%

dates and years in texts

No Comments

No Known Activations