INDEX

Explanations

references to sequential structures or series in text

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

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

 surla

-0.63

PreferredItem

-0.52

 Autorizaciones

-0.49

Identyfik

-0.48

LookAnd

-0.48

 تضيفلها

-0.46

Datuak

-0.46

 distanciation

-0.46

UnknownFieldSet

-0.45

POSITIVE LOGITS

 part

0.46

 continuation

0.41

 חש

0.40

kenalkan

0.40

Part

0.40

writeFileSync

0.39

warnai

0.39

ozat

0.38

Another

0.38

 Part

0.38

Activations Density 0.045%

references to sequential structures or series in text

No Comments

No Known Activations