INDEX

Explanations

negative sentiments or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ArrowToggle

-0.71

паковка

-0.60

prnewswire

-0.57

ControllerAdvice

-0.55

 TAMBÉM

-0.55

kirch

-0.54

getActiveSheet

-0.54

AfterViewInit

-0.52

chou

-0.52

ware

-0.52

POSITIVE LOGITS

 للمعارف

0.84

مصادر

0.77

Демографія

0.69

 الحره

0.65

 Мексичка

0.65

########.

0.64

Portail

0.63

MessageOf

0.63

følgelig

0.63

Royce

0.59

Activations Density 0.136%

negative sentiments or outcomes

No Comments

No Known Activations