INDEX

Explanations

phrases that introduce sources or references, typically starting with "According to"

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

)**

-1.63

ĥ½

-1.56

idenote

-1.44

))**

-1.37

 traces

-1.36

 trace

-1.34

 devoted

-1.34

dab

-1.32

uality

-1.32

 ashamed

-1.28

POSITIVE LOGITS

stown

1.64

endor

1.63

vue

1.62

mathrsfs

1.58

clin

1.56

nel

1.54

enza

1.52

dom

1.51

emente

1.50

à«ĩ

1.49

Activations Density 0.016%

phrases that introduce sources or references, typically starting with "According to"

No Comments

No Known Activations