INDEX

Explanations

expressions related to default settings or configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.70

DTO

-0.64

-0.58

-0.53

::

-0.51

admin

-0.51

-0.50

-0.49

dagog

-0.48

POSITIVE LOGITS

 default

1.67

 defaults

1.46

default

1.42

 Default

1.39

defaults

1.37

 DEFAULT

1.21

Default

1.20

 Defaults

1.19

默认

1.15

 standard

1.13

Activations Density 0.147%

expressions related to default settings or configurations

No Comments

No Known Activations