INDEX

Explanations

time durations and temporal markers in the text

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

 pensiero

-0.36

 darbu

-0.35

 darb

-0.35

depart

-0.35

restre

-0.34

adering

-0.33

 kautta

-0.33

 asamblea

-0.32

 mondta

-0.32

 Dyck

-0.32

POSITIVE LOGITS

Personendaten

0.57

httphttps

0.52

invokeLater

0.52

 autorytatywna

0.52

الحياه

0.49

haviors

0.49

 increí

0.49

 Italijanski

0.48

EndContext

0.48

MigrationBuilder

0.48

Activations Density 0.011%

time durations and temporal markers in the text

No Comments

No Known Activations