INDEX

Explanations

dates and numbers associated with scheduling events or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Portail

-0.72

ObjectContext

-0.71

 дописавши

-0.71

RenderAtEndOf

-0.68

脚注の使い方

-0.64

BeginInit

-0.63

tonsoft

-0.62

Afternoon

-0.61

期刊论文

-0.59

 contextLoads

-0.59

POSITIVE LOGITS

 dates

0.54

 DATES

0.50

 date

0.47

 Dates

0.45

钉

0.45

Affiliation

0.41

 mendatang

0.41

週間

0.41

phie

0.40

ba

0.40

Activations Density 0.096%

dates and numbers associated with scheduling events or occurrences

No Comments

No Known Activations