INDEX

Explanations

references to various configurations or settings within contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/1-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.1.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

-2.72

§

-2.69

Ŀ

-2.52

¿½

-2.51

Į

-2.38

Ī

-2.35

ĸ

-2.34

ľ

-2.26

ī

-2.19

İ

-2.19

POSITIVE LOGITS

 override

1.82

ulates

1.68

lies

1.67

 forth

1.67

ton

1.66

ifies

1.65

 fire

1.61

 horizon

1.59

 aside

1.58

 dictate

1.54

Activations Density 0.127%

references to various configurations or settings within contexts

No Comments

No Known Activations