INDEX

Explanations

specific years related to events

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

 yours

-1.92

 spirit

-1.80

 hers

-1.79

 trace

-1.74

asts

-1.71

 juice

-1.66

 foul

-1.64

 behold

-1.62

 paste

-1.62

 fluids

-1.61

POSITIVE LOGITS

icolor

1.66

RAF

1.65

ental

1.55

à¯ģ

1.54

ienn

1.52

ICD

1.48

Reviewer

1.46

Generation

1.44

IRST

1.44

iento

1.43

Activations Density 0.061%

specific years related to events

No Comments

No Known Activations