INDEX

Explanations

references to media portrayal and discussion of public figures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 fédé

-0.36

 peuples

-0.34

 âmes

-0.33

 rodilla

-0.32

 cáps

-0.32

 votación

-0.31

 receita

-0.30

 debout

-0.30

 reflexión

-0.30

 circonstances

-0.30

POSITIVE LOGITS

 media

2.42

media

2.00

 MEDIA

1.86

 Media

1.81

Media

1.76

媒体

1.71

MEDIA

1.69

 Medien

1.67

 medias

1.66

 médias

1.66

Activations Density 0.317%

references to media portrayal and discussion of public figures and events

No Comments

No Known Activations