INDEX

Explanations

words indicating a transition or additional information within a narrative

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

 Sites

-1.76

 Site

-1.52

 cookies

-1.49

 Primer

-1.38

 Your

-1.34

 Cookies

-1.34

aste

-1.33

 Solution

-1.32

 primers

-1.32

 accountable

-1.32

POSITIVE LOGITS

¿½

1.81

Ŀ

1.79

Ł

1.64

Ļª

1.61

turned

1.55

·

1.52

dated

1.48

eting

1.48

aly

1.47

olding

1.47

Activations Density 0.012%

words indicating a transition or additional information within a narrative

No Comments

No Known Activations