INDEX

Explanations

code snippets related to programming constructs and data structures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Disorder

-1.62

 wounded

-1.53

 Caption

-1.51

 disorder

-1.50

¼

-1.49

 Cause

-1.45

Ill

-1.44

Ĭ

-1.43

ASP

-1.38

 suspect

-1.36

POSITIVE LOGITS

1.79

addr

1.77

ctl

1.75

rame

1.74

ctx

1.61

bsd

1.58

ime

1.53

oyer

1.49

afka

1.48

cfg

1.45

Activations Density 1.068%

code snippets related to programming constructs and data structures

No Comments

No Known Activations