INDEX

Explanations

repetitive patterns or symbols in the text

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

 Professor

-1.43

 Computing

-1.39

 arbitrary

-1.38

Xia

-1.37

 Brownian

-1.36

bl

-1.34

nai

-1.30

let

-1.29

 caution

-1.27

 least

-1.25

POSITIVE LOGITS

ĻĤ

2.57

↵

2.56

↵  âĢĥ

2.56

↵            ↵

2.56

↵

2.56

č↵

2.56

Activations Density 8.204%

repetitive patterns or symbols in the text

No Comments

No Known Activations