INDEX

Explanations

legal terminology and references related to court cases

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

{}

-1.98

ypse

-1.70

!!

-1.57

{};

-1.54

 doesnt

-1.51

 whilst

-1.48

aim

-1.47

 ones

-1.46

tes

-1.46

 difference

-1.43

POSITIVE LOGITS

ĥ½

3.29

¹

3.21

¸

3.10

µ

3.09

·¸

3.08

±

3.04

ģ

3.02

¾

3.00

¶

2.95

ĵ

2.95

Activations Density 0.424%

legal terminology and references related to court cases

No Comments

No Known Activations