INDEX

Explanations

instances of the word "bother" and its variations

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

 deserve

-1.51

 Psychological

-1.48

quin

-1.46

lie

-1.46

IRE

-1.39

enen

-1.37

 rely

-1.37

 depend

-1.37

 Studies

-1.34

>&

-1.33

POSITIVE LOGITS

ľĵ

2.10

¡

2.01

¦

1.86

Ĳ

1.86

Ł

1.82

°

1.81

Ń

1.78

ŀ

1.77

Ļª

1.77

¨

1.76

Activations Density 0.023%

instances of the word "bother" and its variations

No Comments

No Known Activations