INDEX

Explanations

aspects related to limitations, threats, and notable characteristics of systems or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 purpoſe

-0.68

UIControlState

-0.67

 myſelf

-0.66

lapsingToolbar

-0.65

 Majefty

-0.65

новниш

-0.63

 neceff

-0.63



-0.62

 occaf

-0.61

\{\\

-0.60

POSITIVE LOGITS

is

0.83

 adalah

0.71

的是

0.66

คือ

0.66

するのは

0.62

 include

0.59

したのが

0.57

was

0.57

的就是

0.56

 kasarigan

0.54

Activations Density 0.479%

aspects related to limitations, threats, and notable characteristics of systems or features

No Comments

No Known Activations