INDEX

Explanations

references to large-scale systems or operations

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

rile

-1.90

etine

-1.56

ilde

-1.52

ETHOD

-1.51

ÑĥÑĩ

-1.48

 prompt

-1.48

riev

-1.47

 dawn

-1.46

ICES

-1.45

ierno

-1.44

POSITIVE LOGITS

(\>

2.60

 amounts

2.36

 (âī¥

2.29

(>

2.29

(\~

2.17

 enough

2.11

 sized

2.10

 proportions

2.06

 quantities

2.05

 amount

1.95

Activations Density 0.099%

references to large-scale systems or operations

No Comments

No Known Activations