INDEX

Explanations

references to images and credits in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 CreateTagHelper

-0.89

principalTable

-0.89

 Réponses

-0.74

addCriterion

-0.73

MigrationBuilder

-0.72

 estekak

-0.70

 ་་

-0.66

 protoimpl

-0.64

parsedMessage

-0.63

osoba

-0.63

POSITIVE LOGITS

 image

0.68

 Image

0.64

 images

0.63

 Images

0.59

Image

0.55

 photograph

0.54

 photo

0.54

image

0.53

 IMAGES

0.53

 imagem

0.52

Activations Density 0.131%

references to images and credits in the document

No Comments

No Known Activations