INDEX

Explanations

comparisons between entities, particularly in terms of value, quality, and treatment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 propOrder

-0.81

Autoritní

-0.80

 للمعارف

-0.69

 Paglinawan

-0.69

:✨

-0.67

ंदीखरीदारी

-0.67

queryInterface

-0.66

AndEndTag

-0.63

msgTypes

-0.62

RTDA

-0.60

POSITIVE LOGITS

以上に

0.29

any

0.28

demment

0.27

 resident

0.26

 than

0.26

мей

0.26

ẫu

0.25

 Arab

0.25

LENGTH

0.25

Bue

0.25

Activations Density 0.267%

comparisons between entities, particularly in terms of value, quality, and treatment

No Comments

No Known Activations