INDEX

Explanations

legal terminology and references

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã©ric

-1.60

aceut

-1.47

 duty

-1.42

othermal

-1.41

 legally

-1.38

 counseling

-1.36

ologically

-1.36

odox

-1.35

braska

-1.32

iably

-1.32

POSITIVE LOGITS

ľĵ

3.29

ĻĤ

3.00

½

2.97

²

2.96

Ļ

2.75

ĨĴ

2.68

»

2.66

©

2.62

č↵č↵

2.60

Activations Density 2.052%

legal terminology and references

No Comments

No Known Activations