INDEX

Explanations

the word "loose" in various contexts

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

 brighter

-1.48

ories

-1.46

 brave

-1.41

 lack

-1.41

 slightest

-1.38

 wonderful

-1.37

 wonders

-1.37

ris

-1.36

 ease

-1.35

 brightly

-1.35

POSITIVE LOGITS

ģ

3.84

Ģ

3.73

Ľ

3.59

ł

3.58

¡

3.48

ĻĤ

3.40

¼

3.39

½

3.36

®

3.35

¾

3.32

Activations Density 0.024%

the word "loose" in various contexts

No Comments

No Known Activations