INDEX

Explanations

the term "Department" 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

 latter

-1.89

 usual

-1.62

)">

-1.59

 discouraged

-1.58

 word

-1.55

 verb

-1.50

 threatened

-1.49

 forbidden

-1.47

 mercy

-1.45

 questioned

-1.44

POSITIVE LOGITS

¾

2.12

yards

2.00

»¿

1.99

º

1.77

aho

1.73

mans

1.71

İ

1.69

rooms

1.69

yard

1.66

aceut

1.65

Activations Density 0.043%

the term "Department" in various contexts

No Comments

No Known Activations