INDEX

Explanations

terms related to maximum and minimum values or limits

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 autorytatywna

-0.78

max

-0.59

 maksi

-0.57

 الرياضيه

-0.54

マックス

-0.53

 maxim

-0.52

الدراسه

-0.49

:✨

-0.48

 minimum

-0.48

 máximo

-0.48

POSITIVE LOGITS

 Probable

0.37

HasForeignKey

0.37

 finer

0.35

 route

0.35

">//

0.34

 setUsername

0.33

 draft

0.32

 هنوز

0.32

 nochmal

0.32

navigationItem

0.32

Activations Density 0.007%

terms related to maximum and minimum values or limits

No Comments

No Known Activations