INDEX

Explanations

text structured as scientific abstracts or formal summaries

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

dad

-1.73

done

-1.55

hores

-1.54

ÅĽci

-1.44

fax

-1.43

 royalty

-1.42

 fence

-1.39

 lasted

-1.39

phone

-1.38

hold

-1.38

POSITIVE LOGITS

TRODUCTION

1.96

 advances

1.59

 attacks

1.58

ympt

1.57

cribing

1.50

ociation

1.50

theless

1.49

uric

1.44

ensive

1.41

existence

1.40

Activations Density 0.047%

text structured as scientific abstracts or formal summaries

No Comments

No Known Activations