INDEX

Explanations

phrases indicating a growing trend or increasing importance across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 للمعارف

-0.71

expandindo

-0.67

 Мексичка

-0.66

 userSchema

-0.64

Rüyada

-0.63

AnchorStyles

-0.61

bush

-0.60

<?,

-0.58

richlet

-0.57

 teething

-0.57

POSITIVE LOGITS

 increasingly

1.00

越来越多

0.83

越来越

0.80

 coraz

0.69

越來越

0.69

 zuneh

0.65

 semakin

0.63

 progressively

0.63

KURZBESCHREIBUNG

0.59

 Increasing

0.57

Activations Density 0.323%

phrases indicating a growing trend or increasing importance across various contexts

No Comments

No Known Activations