INDEX

Explanations

references to images and photos

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

новниш

-0.42

IUrlHelper

-0.40

 EconPapers

-0.40

RTDA

-0.39

 unknownFields

-0.39

хьтан

-0.38

aurais

-0.38

WriteTagHelper

-0.36

 caráter

-0.36

tagHelperRunner

-0.35

POSITIVE LOGITS

 photograph

0.76

 photographs

0.69

 picture

0.67

 Photograph

0.63

 pictures

0.63

 Photographs

0.60

photograph

0.60

 portrait

0.58

picture

0.57

 photos

0.57

Activations Density 0.290%

references to images and photos

No Comments

No Known Activations

references to images and photos

No Comments

No Known Activations