INDEX

Explanations

numeric patterns or symbols indicating data structure elements

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

 spot

-1.61

 marked

-1.50

abouts

-1.47

amen

-1.44

 crashed

-1.43

ty

-1.41

ctic

-1.38

ila

-1.36

ids

-1.35

 park

-1.34

POSITIVE LOGITS

!/

1.53

 novels

1.50

 fiction

1.47

resis

1.44

 journalism

1.43

...]

1.43

 ourselves

1.41

elif

1.39

 prose

1.39

 Letter

1.38

Activations Density 0.056%

numeric patterns or symbols indicating data structure elements

No Comments

No Known Activations