INDEX

Explanations

terms related to triggers and signaling in operations or functions

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

rl

-1.56

CTIONS

-1.53

thi

-1.48

áĢ¯

-1.46

áĢĲ

-1.46

ibel

-1.45

áĢ

-1.44

HDL

-1.44

TRODUCTION

-1.42

ijn

-1.42

POSITIVE LOGITS

hole

1.61

 deadlines

1.59

 triggers

1.57

 triggering

1.57

holes

1.56

 alarms

1.56

 trigger

1.55

grounds

1.55

 sunset

1.54

 duty

1.53

Activations Density 0.134%

terms related to triggers and signaling in operations or functions

No Comments

No Known Activations