INDEX

Explanations

technical terms or elements related to programming or coding structures

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

 explanation

-1.72

 manifestation

-1.67

\]](

-1.56

hesis

-1.54

 manuscript

-1.47

áĢº

-1.47

Zen

-1.45

iating

-1.39

 manifested

-1.36

 translator

-1.36

POSITIVE LOGITS

banks

1.50

uties

1.47

enne

1.47

loan

1.47

ockey

1.47

pec

1.47

illas

1.47

OTA

1.45

skins

1.44

bserver

1.40

Activations Density 4.855%

technical terms or elements related to programming or coding structures

No Comments

No Known Activations