INDEX

Explanations

specific names or identifiers related to brands or products

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

"?

-1.78

?",

-1.64

inois

-1.57

enburg

-1.57

amento

-1.54

'?

-1.54

↵

-1.53

osing

-1.49

↵

-1.49

lect

-1.47

POSITIVE LOGITS

 budgets

1.62

nee

1.50

eyed

1.49

ifi

1.48

ript

1.45

bit

1.42

BER

1.42

iah

1.41

PRINT

1.41

 Stat

1.39

Activations Density 0.010%

specific names or identifiers related to brands or products

No Comments

No Known Activations