INDEX

Explanations

specific Japanese words and punctuation marks 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

 Roskov

-0.64

Hentet

-0.59

+#+

-0.56

twimg

-0.52

 Chwiliwch

-0.51

fromnode

-0.50

 arşivlendi

-0.48

 Taktlose

-0.46

 NSCoder

-0.46

 Signalez

-0.46

POSITIVE LOGITS

 navideña

0.38

 Nara

0.36

mop

0.36

juna

0.35

CloseOperation

0.35

CWE

0.34

周

0.34

:]:

0.34

timme

0.33

jenih

0.33

Activations Density 0.053%

specific Japanese words and punctuation marks in the text

No Comments

No Known Activations