INDEX

Explanations

information related to technical document formatting and structure

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.0.hook_mlp_out

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

/%

-1.53

 Mathemat

-1.52

 Planck

-1.52

TRODUCTION

-1.48

 sickness

-1.41

 Buddha

-1.39

 likes

-1.38

 Freud

-1.38

 centimeters

-1.37

\]\].

-1.37

POSITIVE LOGITS

ĨĴ

2.39

ķ

2.30

ĥ½

2.13

¡

2.11

Ħ

2.04

ĸ

1.87

²

1.83

§

1.81

¹

1.80

®

1.77

Activations Density 0.010%

information related to technical document formatting and structure

No Comments

No Known Activations