INDEX

Explanations

technical terms related to programming and data structures

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

 branches

-1.46

 franchise

-1.41

 penicillin

-1.37

 endorse

-1.35

tel

-1.34

 whatever

-1.31

 theirs

-1.31

 directory

-1.30

 fuck

-1.30

rid

-1.25

POSITIVE LOGITS

<|outofrange|>

2.83

↵

2.83

↵↵↵

2.83

↵

2.83

↵↵

2.83

↵

2.83

↵

2.83

č↵

2.83

Activations Density 3.288%

technical terms related to programming and data structures

No Comments

No Known Activations