INDEX

Explanations

references to media types and mentions of media in general

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Pickett

-0.74

AndEndTag

-0.70

عط

-0.67

(!__

-0.67

Zag

-0.66

Dob

-0.66

ARR

-0.65

 Acon

-0.64

ntö

-0.64

GetKeyDown

-0.64

POSITIVE LOGITS

 media

1.42

MEDIA

1.40

 Media

1.38

 MEDIA

1.37

 medias

1.29

Media

1.25

media

1.24

 medi

1.12

 Medien

1.05

medi

1.03

Activations Density 0.068%

references to media types and mentions of media in general

No Comments

No Known Activations