INDEX

Explanations

mathematical notations and symbols related to transformations and fields

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

%)$

-0.69

Kathryn

-0.66

Kib

-0.66

')[

-0.64

endal

-0.63

bus

-0.63

CHAPTER

-0.63

IMENTO

-0.63

feira

-0.63

 getResource

-0.62

POSITIVE LOGITS

prime

0.75

 spacy

0.74

ContentAlignment

0.70

′

0.69

AndEndTag

0.66

ViewFeatures

0.66

 consultato

0.65

Swatch

0.65

 honneur

0.65

 nonatomic

0.64

Activations Density 0.256%

mathematical notations and symbols related to transformations and fields

No Comments

No Known Activations